Graph mining

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8" /> <link rel="canonical" href="http://research.google/teams/graph-mining/" /><meta property="og:title" content="Graph mining"><meta property="og:url" content="http://research.google/teams/graph-mining/"><meta property="og:image" content="https://storage.googleapis.com/gweb-research2023-media/images/Open_Graph.width-800.format-jpeg.jpg"><meta property="og:image:secure_url" content="https://storage.googleapis.com/gweb-research2023-media/images/Open_Graph.width-800.format-jpeg.jpg"><meta property="og:type" content="Website"> <title>Graph mining</title> <meta name="viewport" content="width=device-width, initial-scale=1 viewport-fit=cover"/> <link rel="icon" type="image/png" href="/gr/static/assets/favicon.ico"> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> <link rel="preload" href="https://fonts.googleapis.com/css2?family=Product+Sans&family=Google+Sans+Display:ital@0;1&family=Google+Sans:ital,wght@0,400;0,500;0,700;1,400;1,500;1,700&family=Google+Sans+Text:ital,wght@0,400;0,500;0,700;1,400;1,500;1,700&display=swap" as="style"> <link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Product+Sans&family=Google+Sans+Display:ital@0;1&family=Google+Sans:ital,wght@0,400;0,500;0,700;1,400;1,500;1,700&family=Google+Sans+Text:ital,wght@0,400;0,500;0,700;1,400;1,500;1,700&display=swap"> <link href="https://fonts.googleapis.com/css2?family=Roboto+Mono:wght@400;700&display=swap" rel="stylesheet"> <link href="https://www.gstatic.com/glue/cookienotificationbar/cookienotificationbar.min.css" rel="stylesheet" /> <link href="https://www.gstatic.com/glue/v27_1/glue-material.min.css" rel="stylesheet"> <link rel="stylesheet" type="text/css" href="/gr/static/css/googleresearch.css?id=0c26ea1fed8bdd0324f9f4fad1f6a470">  <script>(function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start': new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0], j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src= 'https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f); })(window,document,'script','dataLayer','GTM-K8QBZ7Q'); </script>  </head> <body class=" js-google-tag-wrapper" data-gt-page-path="http://research.google/teams/graph-mining/" data-env="production">  <noscript><iframe src="https://www.googletagmanager.com/ns.html?id=GTM-K8QBZ7Q" height="0" width="0" style="display:none;visibility:hidden"></iframe></noscript>  <header class="global-header glue-header glue-header--single not-glue"> <a href="#page-content" class="glue-header__skip-content">Jump to Content</a> <div class="glue-header__bar glue-header__bar--mobile not-glue"> <div class="glue-header__tier not-glue">  <div class="glue-header__container"> <div class="glue-header__lock-up">  <div class="glue-header__hamburger"> <button class="glue-header__drawer-toggle-btn" aria-label="Open the navigation drawer"> <svg class="glue-icon glue-icon--24px" role="presentation" aria-hidden="true"> <use href="/gr/static/assets/icons/glue-icons.svg#menu"></use> </svg> </button> </div> <div class="glue-header__logo"> <a class="glue-header__logo-link" href="/" title="Google Research">  <div class="glue-header__logo-container"> <svg role="presentation" aria-hidden="true" alt='Google' class="glue-icon glue-icon glue-header__logo-svg"> <use href="/gr/static/assets/icons/glue-icons.svg#google-color-logo"></use> </svg> </div> <span class="glue-header__logo--product">Research</span> </a> </div> </div> </div> </div> </div> <div class="glue-header__bar glue-header__bar--desktop glue-header__drawer"> <div class="glue-header__tier">  <div class="glue-header__container"> <div class="glue-header__lock-up"> <div class="glue-header__logo"> <a class="glue-header__logo-link" href="/" title="Google Research">  <div class="glue-header__logo-container"> <svg role="presentation" aria-hidden="true" alt='Google' class="glue-icon glue-icon glue-header__logo-svg not-glue --dark-logo"> <use href="/gr/static/assets/icons/glue-icons.svg#google-solid-logo"></use> </svg> <svg role="presentation" aria-hidden="true" alt='Google' class="glue-icon glue-icon glue-header__logo-svg --light-logo"> <use href="/gr/static/assets/icons/glue-icons.svg#google-color-logo"></use> </svg> </div> <span class="glue-header__logo--product">Research</span> </a> </div> </div> </div>  <div class="glue-header__container glue-header__container--linkbar"> <nav class="glue-header__link-bar navigation js-gt-global-nav-wrapper"> <ul class="glue-header__list"> <li class="glue-header__item js-sub-nav-parent --parent" data-gt-primary="Who we are" > <button class="glue-header__link js-sub-nav-target" aria-haspopup="true" aria-expanded="false" > <span class=""> Who we are <span class="icon icon--caret"></span> </span> </button> <div class="navigation__sub js-sub-nav" role="menu"> <div class="navigation__sub__container"> <div class="navigation__sub__mobile-heading"> <button class="glue-header__link js-sub-nav-close-mobile"> <span class="sr-text">Back to</span> <span class="icon icon--caret"></span> Who we are <span class="sr-text">menu</span> </button> <hr/> </div> <div class="block-nav_drawer_columns_content"> <div class="navigation__sub--content" data-gt-secondary="Defining the technology of today and tomorrow."> <div class="navigation__sub__wrapper"> <div class="navigation__sub__heading"> <h2 class="headline-3">Defining the technology of today and tomorrow.</h2> </div> <ul class="navigation__sub__columns"> <li data-gt-secondary="Philosophy"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading"> Philosophy </h2> <p class="navigation__sub__columns__description caption">We strive to create an environment conducive to many different types of research across many different time scales and levels of risk.</p> <a href="http://research.google/philosophy/" class="glue-inline-link js-drawer-link" > <span class="sr-text">Learn more about our Philosophy</span> <span aria-hidden="true">Learn more</span> </a> </div> <div class="navigation__sub__columns__mobile"> <a class="glue-header__link" href="http://research.google/philosophy/" > Philosophy </a> </div> </li> <li data-gt-secondary="People"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading"> People </h2> <p class="navigation__sub__columns__description caption">Our researchers drive advancements in computer science through both fundamental and applied research.</p> <a href="http://research.google/people/" class="glue-inline-link js-drawer-link" > <span class="sr-text">Learn more about our People</span> <span aria-hidden="true">Learn more</span> </a> </div> <div class="navigation__sub__columns__mobile"> <a class="glue-header__link" href="http://research.google/people/" > People </a> </div> </li> </ul> </div> </div> </div> </div> </div> </li> <li class="glue-header__item js-sub-nav-parent --parent" data-gt-primary="Research areas" > <button class="glue-header__link js-sub-nav-target" aria-haspopup="true" aria-expanded="false" > <span class=""> Research areas <span class="icon icon--caret"></span> </span> </button> <div class="navigation__sub js-sub-nav" role="menu"> <div class="navigation__sub__container"> <div class="navigation__sub__mobile-heading"> <button class="glue-header__link js-sub-nav-close-mobile"> <span class="sr-text">Back to</span> <span class="icon icon--caret"></span> Research areas <span class="sr-text">menu</span> </button> <hr/> </div> <div class="block-nav_drawer_columns_link_list"> <div class="navigation__sub--list"> <div class="navigation__sub__wrapper"> <ul class="navigation__sub__columns"> <li data-gt-secondary="Research areas"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading">Research areas</h2> <ul> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/" > Explore all research areas </a> </li> </ul> </div> <div class="navigation__sub__columns__mobile"> <button class="glue-header__link js-sub-nav-target" data-panel="nested" role="menuitem" aria-haspopup="true"> Research areas <span class="icon icon--caret"></span> </button> <div class="navigation__nested-sub js-sub-nav-parent"> <div class="navigation__sub__mobile-heading"> <button class="glue-header__link js-sub-nav-close-mobile" role="menuitem" aria-haspopup="true"> <span class="sr-text">Back to</span> <span class="icon icon--caret"></span> Research areas <span class="sr-text">menu</span> </button> <hr/> </div> <ul> <li role="menuitem"> <a href="http://research.google/research-areas/" class="navigation__sub__columns__mobile__link" > Explore all research areas <span> </span> </a> </li> </ul> </div> </div> </li> <li data-gt-secondary="Foundational ML & Algorithms"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading">Foundational ML & Algorithms</h2> <ul> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/algorithms-and-theory/" > Algorithms & Theory </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/data-management/" > Data Management </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/data-mining-and-modeling/" > Data Mining & Modeling </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/information-retrieval-and-the-web/" > Information Retrieval & the Web </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/machine-intelligence/" > Machine Intelligence </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/machine-perception/" > Machine Perception </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/machine-translation/" > Machine Translation </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/natural-language-processing/" > Natural Language Processing </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/speech-processing/" > Speech Processing </a> </li> </ul> </div> <div class="navigation__sub__columns__mobile"> <button class="glue-header__link js-sub-nav-target" data-panel="nested" role="menuitem" aria-haspopup="true"> Foundational ML & Algorithms <span class="icon icon--caret"></span> </button> <div class="navigation__nested-sub js-sub-nav-parent"> <div class="navigation__sub__mobile-heading"> <button class="glue-header__link js-sub-nav-close-mobile" role="menuitem" aria-haspopup="true"> <span class="sr-text">Back to</span> <span class="icon icon--caret"></span> Foundational ML & Algorithms <span class="sr-text">menu</span> </button> <hr/> </div> <ul> <li role="menuitem"> <a href="http://research.google/research-areas/algorithms-and-theory/" class="navigation__sub__columns__mobile__link" > Algorithms & Theory <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/data-management/" class="navigation__sub__columns__mobile__link" > Data Management <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/data-mining-and-modeling/" class="navigation__sub__columns__mobile__link" > Data Mining & Modeling <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/information-retrieval-and-the-web/" class="navigation__sub__columns__mobile__link" > Information Retrieval & the Web <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/machine-intelligence/" class="navigation__sub__columns__mobile__link" > Machine Intelligence <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/machine-perception/" class="navigation__sub__columns__mobile__link" > Machine Perception <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/machine-translation/" class="navigation__sub__columns__mobile__link" > Machine Translation <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/natural-language-processing/" class="navigation__sub__columns__mobile__link" > Natural Language Processing <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/speech-processing/" class="navigation__sub__columns__mobile__link" > Speech Processing <span> </span> </a> </li> </ul> </div> </div> </li> <li data-gt-secondary="Computing Systems & Quantum AI"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading">Computing Systems & Quantum AI</h2> <ul> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/distributed-systems-and-parallel-computing/" > Distributed Systems & Parallel Computing </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/hardware-and-architecture/" > Hardware & Architecture </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/mobile-systems/" > Mobile Systems </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/networking/" > Networking </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/quantum-computing/" > Quantum Computing </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/robotics/" > Robotics </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/security-privacy-and-abuse-prevention/" > Security, Privacy, & Abuse Prevention </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/software-engineering/" > Software Engineering </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/software-systems/" > Software Systems </a> </li> </ul> </div> <div class="navigation__sub__columns__mobile"> <button class="glue-header__link js-sub-nav-target" data-panel="nested" role="menuitem" aria-haspopup="true"> Computing Systems & Quantum AI <span class="icon icon--caret"></span> </button> <div class="navigation__nested-sub js-sub-nav-parent"> <div class="navigation__sub__mobile-heading"> <button class="glue-header__link js-sub-nav-close-mobile" role="menuitem" aria-haspopup="true"> <span class="sr-text">Back to</span> <span class="icon icon--caret"></span> Computing Systems & Quantum AI <span class="sr-text">menu</span> </button> <hr/> </div> <ul> <li role="menuitem"> <a href="http://research.google/research-areas/distributed-systems-and-parallel-computing/" class="navigation__sub__columns__mobile__link" > Distributed Systems & Parallel Computing <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/hardware-and-architecture/" class="navigation__sub__columns__mobile__link" > Hardware & Architecture <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/mobile-systems/" class="navigation__sub__columns__mobile__link" > Mobile Systems <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/networking/" class="navigation__sub__columns__mobile__link" > Networking <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/quantum-computing/" class="navigation__sub__columns__mobile__link" > Quantum Computing <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/robotics/" class="navigation__sub__columns__mobile__link" > Robotics <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/security-privacy-and-abuse-prevention/" class="navigation__sub__columns__mobile__link" > Security, Privacy, & Abuse Prevention <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/software-engineering/" class="navigation__sub__columns__mobile__link" > Software Engineering <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/software-systems/" class="navigation__sub__columns__mobile__link" > Software Systems <span> </span> </a> </li> </ul> </div> </div> </li> <li data-gt-secondary="Science, AI & Society"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading">Science, AI & Society</h2> <ul> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/climate-and-sustainability/" > Climate & Sustainability </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/economics-and-electronic-commerce/" > Economics & Electronic Commerce </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/education-innovation/" > Education Innovation </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/general-science/" > General Science </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/health-bioscience/" > Health & Bioscience </a> </li> <li> <a class="navigation__sub__columns__list-link caption js-drawer-link" href="http://research.google/research-areas/human-computer-interaction-and-visualization/" > Human-Computer Interaction and Visualization </a> </li> </ul> </div> <div class="navigation__sub__columns__mobile"> <button class="glue-header__link js-sub-nav-target" data-panel="nested" role="menuitem" aria-haspopup="true"> Science, AI & Society <span class="icon icon--caret"></span> </button> <div class="navigation__nested-sub js-sub-nav-parent"> <div class="navigation__sub__mobile-heading"> <button class="glue-header__link js-sub-nav-close-mobile" role="menuitem" aria-haspopup="true"> <span class="sr-text">Back to</span> <span class="icon icon--caret"></span> Science, AI & Society <span class="sr-text">menu</span> </button> <hr/> </div> <ul> <li role="menuitem"> <a href="http://research.google/research-areas/climate-and-sustainability/" class="navigation__sub__columns__mobile__link" > Climate & Sustainability <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/economics-and-electronic-commerce/" class="navigation__sub__columns__mobile__link" > Economics & Electronic Commerce <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/education-innovation/" class="navigation__sub__columns__mobile__link" > Education Innovation <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/general-science/" class="navigation__sub__columns__mobile__link" > General Science <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/health-bioscience/" class="navigation__sub__columns__mobile__link" > Health & Bioscience <span> </span> </a> </li> <li role="menuitem"> <a href="http://research.google/research-areas/human-computer-interaction-and-visualization/" class="navigation__sub__columns__mobile__link" > Human-Computer Interaction and Visualization <span> </span> </a> </li> </ul> </div> </div> </li> </ul> </div> </div></div> </div> </div> </li> <li class="glue-header__item js-sub-nav-parent --parent" data-gt-primary="Our work" > <button class="glue-header__link js-sub-nav-target" aria-haspopup="true" aria-expanded="false" > <span class=""> Our work <span class="icon icon--caret"></span> </span> </button> <div class="navigation__sub js-sub-nav" role="menu"> <div class="navigation__sub__container"> <div class="navigation__sub__mobile-heading"> <button class="glue-header__link js-sub-nav-close-mobile"> <span class="sr-text">Back to</span> <span class="icon icon--caret"></span> Our work <span class="sr-text">menu</span> </button> <hr/> </div> <div class="block-nav_drawer_columns_content"> <div class="navigation__sub--content" data-gt-secondary=""> <div class="navigation__sub__wrapper"> <ul class="navigation__sub__columns"> <li data-gt-secondary="Projects"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading"> Projects </h2> <p class="navigation__sub__columns__description caption">We regularly open-source projects with the broader research community and apply our developments to Google products.</p> <a href="http://research.google/resources/our-projects/" class="glue-inline-link js-drawer-link" > <span class="sr-text">Learn more about our Projects</span> <span aria-hidden="true">Learn more</span> </a> </div> <div class="navigation__sub__columns__mobile"> <a class="glue-header__link" href="http://research.google/resources/our-projects/" > Projects </a> </div> </li> <li data-gt-secondary="Publications"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading"> Publications </h2> <p class="navigation__sub__columns__description caption">Publishing our work allows us to share ideas and work collaboratively to advance the field of computer science.</p> <a href="http://research.google/pubs/" class="glue-inline-link js-drawer-link" > <span class="sr-text">Learn more about our Publications</span> <span aria-hidden="true">Learn more</span> </a> </div> <div class="navigation__sub__columns__mobile"> <a class="glue-header__link" href="http://research.google/pubs/" > Publications </a> </div> </li> <li data-gt-secondary="Resources"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading"> Resources </h2> <p class="navigation__sub__columns__description caption">We make products, tools, and datasets available to everyone with the goal of building a more collaborative ecosystem.</p> <a href="http://research.google/resources/" class="glue-inline-link js-drawer-link" > <span class="sr-text">Learn more about our Resources</span> <span aria-hidden="true">Learn more</span> </a> </div> <div class="navigation__sub__columns__mobile"> <a class="glue-header__link" href="http://research.google/resources/" > Resources </a> </div> </li> </ul> </div> </div> </div> </div> </div> </li> <li class="glue-header__item js-sub-nav-parent --parent" data-gt-primary="Programs & events" > <button class="glue-header__link js-sub-nav-target" aria-haspopup="true" aria-expanded="false" > <span class=""> Programs & events <span class="icon icon--caret"></span> </span> </button> <div class="navigation__sub js-sub-nav" role="menu"> <div class="navigation__sub__container"> <div class="navigation__sub__mobile-heading"> <button class="glue-header__link js-sub-nav-close-mobile"> <span class="sr-text">Back to</span> <span class="icon icon--caret"></span> Programs & events <span class="sr-text">menu</span> </button> <hr/> </div> <div class="block-nav_drawer_columns_content"> <div class="navigation__sub--content" data-gt-secondary="Shaping the future, together."> <div class="navigation__sub__wrapper"> <div class="navigation__sub__heading"> <h2 class="headline-3">Shaping the future, together.</h2> <a href="http://research.google/programs-and-events/" class="js-drawer-link" > Collaborate with us </a> </div> <ul class="navigation__sub__columns"> <li data-gt-secondary="Student programs"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading"> Student programs </h2> <p class="navigation__sub__columns__description caption">Supporting the next generation of researchers through a wide range of programming.</p> <a href="http://research.google/programs-and-events/student-engagement/" class="glue-inline-link js-drawer-link" > <span class="sr-text">Learn more about our Student programs</span> <span aria-hidden="true">Learn more</span> </a> </div> <div class="navigation__sub__columns__mobile"> <a class="glue-header__link" href="http://research.google/programs-and-events/student-engagement/" > Student programs </a> </div> </li> <li data-gt-secondary="Faculty programs"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading"> Faculty programs </h2> <p class="navigation__sub__columns__description caption">Participating in the academic research community through meaningful engagement with university faculty.</p> <a href="http://research.google/programs-and-events/faculty-engagement/" class="glue-inline-link js-drawer-link" > <span class="sr-text">Learn more about our Faculty programs</span> <span aria-hidden="true">Learn more</span> </a> </div> <div class="navigation__sub__columns__mobile"> <a class="glue-header__link" href="http://research.google/programs-and-events/faculty-engagement/" > Faculty programs </a> </div> </li> <li data-gt-secondary="Conferences & events"> <div class="navigation__sub__columns__desktop"> <h2 class="headline-6 navigation__sub__columns__heading"> Conferences & events </h2> <p class="navigation__sub__columns__description caption">Connecting with the broader research community through events is essential for creating progress in every aspect of our work.</p> <a href="http://research.google/conferences-and-events/" class="glue-inline-link js-drawer-link" > <span class="sr-text">Learn more about our Conferences & events</span> <span aria-hidden="true">Learn more</span> </a> </div> <div class="navigation__sub__columns__mobile"> <a class="glue-header__link" href="http://research.google/conferences-and-events/" > Conferences & events </a> </div> </li> </ul> <div class="navigation__sub__cta"> <a class="glue-button glue-button--high-emphasis js-drawer-link" href="http://research.google/programs-and-events/" target="_blank" rel="noreferrer noopener" > Collaborate with us </a> </div> </div> </div> </div> </div> </div> </li> <li class="glue-header__item " data-gt-primary="Careers" > <a class="glue-header__link " href="http://research.google/careers/" > <span class=""> Careers </span> </a> </li> <li class="glue-header__item " data-gt-primary="Blog" > <a class="glue-header__link " href="http://research.google/blog/" > <span class=""> Blog </span> </a> </li> </ul> </nav> </div>  <div class="glue-header__search js-header-search"> <div class="glue-header__search__input"> <div class="search-input " data-type="header"> <input type="search" class="caption --empty-search js-search-bar js-gt-search-input" placeholder="Search"> <button class="search-input__button --search js-gt-search-btn"> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px "> <use href="/gr/static/assets/icons/glue-icons.svg#search"></use> </svg> </button> <button class="search-input__button --clear"> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px "> <use href="/gr/static/assets/icons/glue-icons.svg#close"></use> </svg> </button> </div> </div> <button class="glue-header__search__btn js-header-search-btn"> <svg role="presentation" aria-hidden="true" aria-hidden="true" class="glue-icon glue-icon--24px search"> <use href="/gr/static/assets/icons/glue-icons.svg#search"></use> </svg> <svg role="presentation" aria-hidden="true" aria-hidden="true" class="glue-icon glue-icon--24px close"> <use href="/gr/static/assets/icons/glue-icons.svg#close"></use> </svg> <span class="sr-text js-header-search-sr-text">Search</span> </button> </div> </div> </div> <div class="glue-header__drawer-backdrop"> <div class="glue-header__mobile_close"> <button class="glue-header__drawer-toggle-btn js-mobile-nav-close" aria-label="Close the navigation drawer"> <svg class="glue-icon glue-icon--24px" role="presentation" aria-hidden="true"> <use href="/gr/static/assets/icons/glue-icons.svg#close"></use> </svg> </button> </div> </div> </header> <main id="page-content"> <section class="primary-hero --theme-dark" data-gt-id="primary_hero" data-gt-component-name="None"> <div class="glue-page"> <div class="glue-grid primary-hero__grid-wrapper"> <div class="glue-grid__col glue-grid__col--span-6 glue-grid__col--span-7-md glue-grid__col--span-12-sm primary-hero__text"> <h1 class="primary-hero__heading primary-hero__heading--small headline-1">Graph mining</h1> <div class="primary-hero__body --desktop"> <p class="body"><p data-block-key="v5tgb">Our mission is to build the most scalable library for graph algorithms and analysis and apply it to a multitude of Google products.</p></p> <div class="primary-hero__ctas"> </div> </div> </div> <div class="glue-grid__col glue-grid__col--span-6 glue-grid__col--span-5-md glue-grid__col--span-12-sm"> <img src="https://storage.googleapis.com/gweb-research2023-media/original_images/graph-mining.jpg" alt="graphs" > <div class="primary-hero__body --mobile"> <p class="body"><p data-block-key="v5tgb">Our mission is to build the most scalable library for graph algorithms and analysis and apply it to a multitude of Google products.</p></p> <div class="primary-hero__ctas"> </div> </div> </div> </div> </div> </section> <div class="glue-page glue-grid event-detail-page__grid"> <section class="glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md "> <div class="event-detail-page__summary"> </div> <div class="quicklinks-wrapper--mobile"> </div> </section> </div> <section class="offset-two-up --theme-light --no-padding-top" data-gt-id="offset_two_up" data-gt-component-name="None"> <div class="glue-page glue-grid"> <div class="offset-two-up__left-col glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-3-lg"> <h2 class="offset-two-up__headline headline-3">About the team</h2> </div> <div class="glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-9-lg"> <section class="component-as-block --no-vertical-padding"> <div class="rich-text --theme- --mode-subcomponent" data-gt-id="rich_text" data-gt-component-name="None"> <p data-block-key="ol1gj">We formalize data mining and machine learning challenges as graph problems and perform fundamental research in those fields leading to publications in top venues. Our algorithms and systems are used in a wide array of Google products such as Search, YouTube, AdWords, Play, Maps, and Social.</p> </div> </section> </div> </div> </section> <section class="offset-two-up --theme-dark --no-padding-bottom" data-gt-id="offset_two_up" data-gt-component-name="None"> <div class="glue-page glue-grid"> <div class="offset-two-up__left-col glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-3-lg"> <h2 class="offset-two-up__headline headline-3">Team focus summaries</h2> </div> <div class="glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-9-lg"> <section class="component-as-block --no-padding-top"> <div class="accordion --no-padding-top" data-gt-id="accordion" data-gt-component-name="None"> <div class="glue-expansion-panels"> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-large-scale-clustering-and-connected-components-1-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-large-scale-clustering-and-connected-components-1-content"> <span class="glue-expansion-panel__header-text">Large-Scale Clustering and Connected Components</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-large-scale-clustering-and-connected-components-1-content"> <div class="accordion__item__content"> <div> <p data-block-key="z7cid">Our team specializes in clustering at Google scale, efficiently implementing many different algorithms including hierarchical agglomerative clustering, correlation clustering, k-means clustering, DBSCAN, and connected components. Our methods scale to graphs with trillions of edges using multiple machines and can efficiently handle graphs of tens of billions of edges on a single multicore machine. The clustering library powers over a hundred different use-cases across Google.</p> </div> </div> </div> </div> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-graph-neural-networks-and-graph-embeddings-2-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-graph-neural-networks-and-graph-embeddings-2-content"> <span class="glue-expansion-panel__header-text">Graph Neural Networks and Graph Embeddings</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-graph-neural-networks-and-graph-embeddings-2-content"> <div class="accordion__item__content"> <div> <p data-block-key="z3fkc">Our team specializes in large-scale learning on graph-structured data. We push the boundary on scalability, efficiency, and flexibility of our methods, informed by the complex heterogeneous systems abundant in our real-world industrial setting. In pursuit of scalability, we leverage both algorithmic improvements and novel hardware architectures. Our team develops and maintains <a href="https://github.com/tensorflow/gnn" target="_blank" rel="noopener noreferrer">TensorFlow-GNN</a>, a library for training graph neural networks at Google scale.</p> </div> </div> </div> </div> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-large-scale-balanced-partitioning-3-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-large-scale-balanced-partitioning-3-content"> <span class="glue-expansion-panel__header-text">Large-Scale balanced partitioning</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-large-scale-balanced-partitioning-3-content"> <div class="accordion__item__content"> <div> <p data-block-key="xyw3q">Balanced Partitioning splits a large graph into roughly equal parts while minimizing cut size. The problem of “fairly” dividing a graph occurs in a number of contexts, such as assigning work in a distributed processing environment. Our techniques provided a 40% drop in multi-shard queries in Google Maps driving directions, saving a significant amount of CPU usage.</p> </div> </div> </div> </div> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-large-scale-link-modeling-4-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-large-scale-link-modeling-4-content"> <span class="glue-expansion-panel__header-text">Large-Scale link modeling</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-large-scale-link-modeling-4-content"> <div class="accordion__item__content"> <div> <p data-block-key="xyw3q">Our similarity ranking and centrality metrics serve as good features for understanding the characteristics of large graphs. They allow the development of link models useful for both link prediction and anomalous link discovery. Our tool Grale learns a similarity function that models the link relationships present in data.</p> </div> </div> </div> </div> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-large-scale-similarity-ranking-5-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-large-scale-similarity-ranking-5-content"> <span class="glue-expansion-panel__header-text">Large-Scale similarity ranking</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-large-scale-similarity-ranking-5-content"> <div class="accordion__item__content"> <div> <p data-block-key="xyw3q">Our research in pairwise similarity ranking has produced a number of innovative methods, which we have published at top conferences such as <a href="https://dl.acm.org/conference/www" target="_blank" rel="noopener noreferrer"><b>WWW</b></a>, <a href="https://icml.cc/" target="_blank" rel="noopener noreferrer"><b>ICML</b></a>, and <a href="https://www.vldb.org/conference.html" target="_blank" rel="noopener noreferrer"><b>VLDB</b></a>. We maintain a library of similarity algorithms including distributed <a href="https://research.google/pubs/pub42479/"><b>Personalized PageRank</b></a>, <a href="https://ai.googleblog.com/2016/09/research-from-vldb-2016-improved-friend.html" target="_blank" rel="noopener noreferrer"><b>Egonet similarity</b></a>, and others.</p> </div> </div> </div> </div> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-public-private-graph-computation-6-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-public-private-graph-computation-6-content"> <span class="glue-expansion-panel__header-text">Public-private graph computation</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-public-private-graph-computation-6-content"> <div class="accordion__item__content"> <div> <p data-block-key="xyw3q">Our research on novel models of graph computation addresses important issues of privacy in graph mining. Specifically, we present techniques to efficiently solve graph problems, including computing clustering, centrality scores and shortest path distances for each node, based on its personal view of the private data in the graph while preserving the privacy of each user.</p> </div> </div> </div> </div> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-streaming-and-dynamic-graph-algorithms-7-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-streaming-and-dynamic-graph-algorithms-7-content"> <span class="glue-expansion-panel__header-text">Streaming and dynamic graph algorithms</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-streaming-and-dynamic-graph-algorithms-7-content"> <div class="accordion__item__content"> <div> <p data-block-key="xyw3q">We perform innovative research analyzing massive dynamic graphs. We have developed efficient algorithms for computing densest subgraph and triangle counting which operate even when subject to high velocity streaming updates.</p> </div> </div> </div> </div> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-large-scale-centrality-ranking-8-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-large-scale-centrality-ranking-8-content"> <span class="glue-expansion-panel__header-text">Large-Scale centrality ranking</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-large-scale-centrality-ranking-8-content"> <div class="accordion__item__content"> <div> <p data-block-key="xyw3q">Google’s most famous algorithm, PageRank, is a method for computing importance scores for vertices of a directed graph. In addition to PageRank, we have scalable implementations of several other centrality scores, such as harmonic centrality.</p> </div> </div> </div> </div> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-large-scale-graph-building-9-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-large-scale-graph-building-9-content"> <span class="glue-expansion-panel__header-text">Large-Scale graph building</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-large-scale-graph-building-9-content"> <div class="accordion__item__content"> <div> <p data-block-key="xyw3q">The <a href="http://google.github.io/guava/releases/22.0/api/docs/com/google/common/graph/package-summary.html" target="_blank" rel="noopener noreferrer"><b>GraphBuilder library</b></a> can convert data from a metric space (such as document text) into a similarity graph. GraphBuilder scales to massive datasets by applying fast locality sensitive hashing and neighborhood search.</p> </div> </div> </div> </div> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-graph-based-sampling-10-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-graph-based-sampling-10-content"> <span class="glue-expansion-panel__header-text">Graph-based sampling</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-graph-based-sampling-10-content"> <div class="accordion__item__content"> <div> <p data-block-key="z3fkc">Distributed graph-based sampling has proved critical to various applications in active learning and data summarization, where the graph reveals signals about density and multi-hop connections. Combined with deep learning, we tackle provably hard problems and differentiable sampling helps GNN scalability too.</p> </div> </div> </div> </div> <div class="glue-expansion-panel"> <h3 class="glue-expansion-panel__toggle js-gt-accordion-item"> <span class="glue-expansion-panel__button" id="accordion-panel-ml-compiler-optimization-11-toggle" data-glue-expansion-panel-toggle-for="accordion-panel-ml-compiler-optimization-11-content"> <span class="glue-expansion-panel__header-text">ML compiler optimization</span> <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--18px glue-expansion-panel__header-arrow"> <use href="/gr/static/assets/icons/glue-icons.svg#expand-more"></use> </svg> </span> </h3> <div class="glue-expansion-panel__content" id="accordion-panel-ml-compiler-optimization-11-content"> <div class="accordion__item__content"> <div> <p data-block-key="ij3qw">We design and implement graph-based optimization techniques to improve the performance of ML compilers (e.g., XLA). For example, we replaced heuristic-based cost models with graph neural networks (GNNs), achieving significant training and serving speed-ups (see our external <a href="http://research.google/pubs/tpugraphs-performance-prediction-datasets-on-large-tensor-computational-graphs/">TpuGraphs benchmarks</a> and <a href="http://research.google/pubs/learning-large-graph-property-prediction-via-graph-segment-training/">large-scale GNN</a>). We have also deployed model partitioning algorithms that split ML computation graphs across TPUs for <a href="http://research.google/pubs/partitioning-computation-graphs-for-pipeline-parallelism-with-approximation-guarantees/">pipeline parallelism</a>, as well as designed novel methods to certify that these partitions are near-optimal.</p> </div> </div> </div> </div> </div> </div> </section> </div> </div> </section> <section class="offset-two-up --theme-light both" data-gt-id="offset_two_up" data-gt-component-name="None"> <div class="glue-page glue-grid"> <div class="offset-two-up__left-col glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-3-lg"> <h2 class="offset-two-up__headline headline-3">Featured publications</h2> </div> <div class="glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-9-lg"> <section class="component-as-block --no-vertical-padding"> <div class="publications-list --theme-light row-card-list" data-hot-swap="pub-list" data-gt-id="publications_list" data-gt-component-name="None"> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/talk-like-a-graph-encoding-graphs-for-large-language-models/ > Talk like a Graph: Encoding Graphs for Large Language Models </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/108300/"> Bahar Fatemi </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/bryanperozzi/"> Bryan Perozzi </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/jonathanhalcrow/"> Jonathan Halcrow </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> ICLR (2024) </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contentgraphs-are-a-powerful-tool-for-rep tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contentgraphs-are-a-powerful-tool-for-rep" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance. Reasoning on graphs is essential for drawing inferences about the relationships between entities in a complex system, and to identify hidden patterns and trends. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with large language models (LLMs) remains an understudied problem. In this work, we perform the first comprehensive study of encoding graph-structured data as text for consumption by LLMs. We show that LLM performance on graph reasoning tasks varies on three fundamental levels: (1) the graph encoding method, (2) the nature of the graph task itself, and (3) interestingly, the very structure of the graph considered. These novel results provide valuable insight on strategies for encoding graphs as text. Using these insights we illustrate how the correct choice of encoders can boost performance on graph reasoning tasks inside LLMs by 4.8% to 61.8%, depending on the task.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/talk-like-a-graph-encoding-graphs-for-large-language-models/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/measuring-re-identification-risk/ > Measuring Re-identification Risk </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/cjcarey/"> CJ Carey </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Travis Dick </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/alessandroepasto/"> Alessandro Epasto </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Adel Javanmard </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Josh Karlin </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/author3286/"> Shankar Kumar </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/105168/"> Andres Munoz Medina </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/mirrokni/"> Vahab Mirrokni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Gabriel Henrique Nunes </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/sergeivassilvitskii/"> Sergei Vassilvitskii </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/108328/"> Peilin Zhong </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> SIGMOD (2023) </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contentcompact-user-representations-such tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contentcompact-user-representations-such" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">Compact user representations (such as embeddings) form the backbone of personalization services. In this work, we present a new theoretical framework to measure re-identification risk in such user representations. Our framework, based on hypothesis testing, formally bounds the probability that an attacker may be able to obtain the identity of a user from their representation. As an application, we show how our framework is general enough to model important real-world applications such as the Chrome's Topics API for interest-based advertising. We complement our theoretical bounds by showing provably good attack algorithms for re-identification that we use to estimate the re-identification risk in the Topics API. We believe this work provides a rigorous and interpretable notion of re-identification risk and a framework to measure it that can be used to inform real-world applications.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/measuring-re-identification-risk/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/near-optimal-private-and-scalable-k-clustering/ > Near-Optimal Private and Scalable k-Clustering </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/107320/"> Vincent Pierre Cohen-addad </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/alessandroepasto/"> Alessandro Epasto </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/mirrokni/"> Vahab Mirrokni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Shyam Narayanan </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/108328/"> Peilin Zhong </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> NeurIPS 2022 (2022) </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contentwe-study-the-differentially-privat tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contentwe-study-the-differentially-privat" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">We study the differentially private (DP) $k$-means and $k$-median clustering problems of $n$ points in $d$-dimensional Euclidean space in the massively parallel computation (MPC) model. We provide two near-optimal algorithms where the near-optimality is in three aspects: they both achieve (1). $O(1)$ parallel computation rounds, (2). near-linear in $n$ and polynomial in $k$ total computational work (i.e., near-linear running time in the sequential setting), (3). $O(1)$ relative approximation and $\text{poly}(k, d)$ additive error, where $\Omega(1)$ relative approximation is provably necessary even for any polynomial-time non-private algorithm, and $\Omega(k)$ additive error is a provable lower bound for any polynomial-time DP $k$-means/median algorithm. Our two algorithms provide a tradeoff between the relative approximation and the additive error: the first has $O(1)$ relative approximation and $\sim (k^{2.5} + k^{1.01} \sqrt{d})$ additive error, and the second one achieves $(1+\gamma)$ relative approximation to the optimal non-private algorithm for an arbitrary small constant $\gamma>0$ and with $\text{poly}(k, d)$ additive error for a larger polynomial dependence on $k$ and $d$. To achieve our result, we develop a general framework which partitions the data and reduces the DP clustering problem for the entire dataset to the DP clustering problem for each part. To control the blow-up of the additive error introduced by each part, we develop a novel charging argument which might be of independent interest.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/near-optimal-private-and-scalable-k-clustering/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/optimal-distributed-submodular-optimization-via-sketching/ > Optimal Distributed Submodular Optimization via Sketching </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/bateni/"> MohammadHossein Bateni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Hossein Esfandiari </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/mirrokni/"> Vahab Mirrokni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2018), pp. 1138-1147 </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contentas-an-important-special-case-of-su tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contentas-an-important-special-case-of-su" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">As an important special case of submodular optimization problems, coverage problems are a central problem in optimization with a wide range of applications in data mining and machine learning. As we need to handle larger and larger data sets, there is a clear need to develop distributed solutions to these problems. While several results have been developed for distributed coverage maximizations, all the existing method have notable limitations, e.g., they all achieve either suboptimal approximation guarantees or suboptimal space and memory complexities. Moreover, most previous results for submodular maximization either explicitly or implicitly assume that one has a value oracle access to the submodular function. Such a value oracle for coverage functions has the following form: given a subfamily of (input) subsets, determine the size of the union of the subsets in this subfamily.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/optimal-distributed-submodular-optimization-via-sketching/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/tackling-provably-hard-representative-selection-via-graph-neural-networks/ > Tackling Provably Hard Representative Selection via Graph Neural Networks </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/107839/"> Anton Tsitsulin </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/bryanperozzi/"> Bryan Perozzi </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/hosseinesfandiari/"> Hossein Esfandiari </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/108296/"> Mehran Kazemi </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/bateni/"> Mohammad "Hossein" Bateni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/mirrokni/"> Vahab Mirrokni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/107300/"> Deepak Ramachandran </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Transactions on Machine Learning Research (2023) </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contentrepresentative-selection-rs-is-t tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contentrepresentative-selection-rs-is-t" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">Representative Selection (RS) is the problem of finding a small subset of exemplars from a dataset that is representative of the dataset. In this paper, we study RS for attributed graphs, and focus on finding representative nodes that optimize the accuracy of a model trained on the selected representatives. Theoretically, we establish a new hardness result for RS (in the absence of a graph structure) by proving that a particular, highly practical variant of it (RS for Learning) is hard to approximate in polynomial time within any reasonable factor, which implies a significant potential gap between the optimum solution of widely-used surrogate functions and the actual accuracy of the model. We then study the setting where a (homophilous) graph structure is available, or can be constructed, between the data points. We show that with an appropriate modeling approach, the presence of such a structure can turn a hard RS (for learning) problem into one that can be effectively solved. To this end, we develop RS-GNN, a representation learning-based RS model based on Graph Neural Networks. Empirically, we demonstrate the effectiveness of RS-GNN on problems with predefined graph structures as well as problems with graphs induced from node feature similarities, by showing that RS-GNN achieves significant improvements over established baselines on a suite of eight benchmarks.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/tackling-provably-hard-representative-selection-via-graph-neural-networks/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/terahac-hierarchical-agglomerative-clustering-of-trillion-edge-graphs/ > TeraHAC: Hierarchical Agglomerative Clustering of Trillion-Edge Graphs </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/jasonlee/"> Jason Lee </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/105517/"> Jakub Łącki </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/laxmandhulipala/"> Laxman Dhulipala </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/mirrokni/"> Vahab Mirrokni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> SIGMOD'24 (2023) </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contentwe-introduceterahac-a-1epsilon tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contentwe-introduceterahac-a-1epsilon" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">We introduceTeraHAC, a (1+epsilon)-approximate hierarchical agglomerative clustering (HAC) algorithm whichs cales to trillion-edge graphs. Our algorithm is based on a new approach to computing (1+epsilon)-approximate HAC, which is a novel combination of the nearest-neighbor chain algorithm and the notion of (1+epsilon)-approximate HAC. Our approach allows us to partition the graph among multiple machines and make significant progress in computing the clustering within each partition before any communication with other partitions is needed.We evaluate TeraHAC on a number of real-world and synthetic graphs of up to 8 trillion edges. We show that TeraHAC requires over 100x fewer rounds compared to previously known approaches for computing HAC. It is up to 8.3x faster than SCC, the state-of-the-art distributed algorithm for hierarchical clustering, while achieving 1.16x higher quality. In fact, TeraHAC essentially retains the quality of the celebrated HAC algorithm while significantly improving the running time.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/terahac-hierarchical-agglomerative-clustering-of-trillion-edge-graphs/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/massively-parallel-computation-via-remote-memory-access/ > Massively Parallel Computation via Remote Memory Access </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/hosseinesfandiari/"> Hossein Esfandiari </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/105517/"> Jakub Łącki </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Laxman Dhulipala </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Soheil Behnezhad </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/mirrokni/"> Vahab Mirrokni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Warren Schudy </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> SPAA 2019 </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contentwe-introduce-the-adaptive-massivel tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contentwe-introduce-the-adaptive-massivel" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">We introduce the Adaptive Massively Parallel Computation (AMPC) model, which is an extension of the widely popular Massively Parallel Computation (MPC) model. At a high level, the AMPC model strengthens the MPC model by storing all messages sent within a round in a distributed data store. In the following round all machines are provided with random read access to the data store, subject to the same constraints on the total amount of communication as in the MPC model. Our model is inspired by the previous empirical studies of distributed graph algorithms using MapReduce and a distributed hash table service. This extension allows us to give new graph algorithms with much lower round complexities compared to the best known solutions in the MPC model. In particular, in the AMPC model we show how to solve maximal independent set in O(1) rounds, and connectivity/minimum spanning tree in O(log log_{m/n} n) rounds, which is an exponential improvement upon the best known algorithms in the MPC model with sublinear space per machine. Our results imply that the 2-Cycle conjecture, the most popular hardness conjecture in the MPC model, does not hold in the AMPC model.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/massively-parallel-computation-via-remote-memory-access/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/affinity-clustering-hierarchical-clustering-at-scale/ > Affinity Clustering: Hierarchical Clustering at Scale </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/bateni/"> MohammadHossein Bateni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Soheil Behnezhad </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Mahsa Derakhshan </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> MohammadTaghi Hajiaghayi </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Raimondas Kiveris </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/silviolattanzi/"> Silvio Lattanzi </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/mirrokni/"> Vahab Mirrokni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> NIPS 2017, pp. 6867-6877 </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contentgraph-clustering-is-a-fundamental tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contentgraph-clustering-is-a-fundamental" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">Graph clustering is a fundamental task in many data-mining and machine-learning pipelines. In particular, identifying good hierarchical clustering structure is at the same time a fundamental and challenging problem for several applications. In many applications, the amount of data to analyze is increasing at an astonishing rate each day. Hence there is a need for new solutions to efficiently compute effective hierarchical clusterings on such huge data. In this paper, we propose algorithms to address this problem. First, we analyze minimum spanning tree-based clustering algorithms and their corresponding hierarchical clusterings. In particular we consider classic single-linkage clustering based on Kruskal's algorithm and a variation of Boruvka algorithm that we call affinity clustering and prove new interesting properties of these clusterings via the concept of certificates. Then we present new algorithms in the MapReduce model and their efficient real world implementations via Distributed Hash Tables (DHTs). Our MapReduce algorithms indeed improve upon the previous MapReduce algorithms for finding a minimum spanning tree in graphs as well. Finally we show experimentally that our algorithms are scalable for huge data and competitive with state-of-the-art algorithms. In particular we show that Affinity Clustering is in practice superior to several state-of-the-art clustering algorithms.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/affinity-clustering-hierarchical-clustering-at-scale/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/distributed-balanced-partitioning-via-linear-embedding/ > Distributed Balanced Partitioning via Linear Embedding </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/106559/"> Kevin Aydin </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/bateni/"> Mohammadhossein Bateni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/mirrokni/"> Vahab Mirrokni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Ninth ACM International Conference on Web Search and Data Mining (WSDM), ACM (2016), pp. 387-396 </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contentbalanced-partitioning-is-often-a-c tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contentbalanced-partitioning-is-often-a-c" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">Balanced partitioning is often a crucial first step in solving large-scale graph optimization problems: in some cases, a big graph is chopped into pieces that fit on one machine to be processed independently before stitching the results together, leading to certain suboptimality from the interaction among different pieces. In other cases, links between different parts may show up in the running time and/or network communications cost, hence the desire to have small cut size. We study a distributed balanced partitioning problem where the goal is to partition the vertices of a given graph into k pieces, minimizing the total cut size. Our algorithm is composed of a few steps that are easily implementable in distributed computation frameworks, e.g., MapReduce. The algorithm first embeds nodes of the graph onto a line, and then processes nodes in a distributed manner guided by the linear embedding order. We examine various ways to find the first embedding, e.g., via a hierarchical clustering or Hilbert curves. Then we apply four different techniques such as local swaps, minimum cuts on partition boundaries, as well as contraction and dynamic programming. Our empirical study compares the above techniques with each other, and to previous work in distributed algorithms, e.g., a label propagation method [34], FENNEL [32] and Spinner [23]. We report our results both on a private map graph and several public social networks, and show that our results beat previous distributed algorithms: we notice, e.g., 15-25% reduction in cut size over [34]. We also observe that our algorithms allow for scalable distributed implementation for any number of partitions. Finally, we apply our techniques for the Google Maps Driving Directions to minimize the number of multi-shard queries with the goal of saving in CPU usage. During live experiments, we observe an ≈ 40% drop in the number of multi-shard queries when comparing our method with a standard geography-based method.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/distributed-balanced-partitioning-via-linear-embedding/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/distributed-graph-algorithmics-theory-and-practice/ > Distributed Graph Algorithmics: Theory and Practice </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/silviolattanzi/"> Silvio Lattanzi </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/mirrokni/"> Vahab S. Mirrokni </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> WSDM (2015), pp. 419-420 </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contentas-a-fundamental-tool-in-modeling tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contentas-a-fundamental-tool-in-modeling" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">As a fundamental tool in modeling and analyzing social, and information networks, large-scale graph mining is an important component of any tool set for big data analysis. Processing graphs with hundreds of billions of edges is only possible via developing distributed algorithms under distributed graph mining frameworks such as MapReduce, Pregel, Gigraph, and alike. For these distributed algorithms to work well in practice, we need to take into account several metrics such as the number of rounds of computation and the communication complexity of each round. For example, given the popularity and ease-of-use of MapReduce framework, developing practical algorithms with good theoretical guarantees for basic graph algorithms is a problem of great importance. In this tutorial, we first discuss how to design and implement algorithms based on traditional MapReduce architecture. In this regard, we discuss various basic graph theoretic problems such as computing connected components, maximum matching, MST, counting triangle and overlapping or balanced clustering. We discuss a computation model for MapReduce and describe the sampling, filtering, local random walk, and core-set techniques to develop efficient algorithms in this framework. At the end, we explore the possibility of employing other distributed graph processing frameworks. In particular, we study the effect of augmenting MapReduce with a distributed hash table (DHT) service and also discuss the use of a new graph processing framework called ASYMP based on asynchronous message-passing method. In particular, we will show that using ASyMP, one can improve the CPU usage, and achieve significantly improved running time.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/distributed-graph-algorithmics-theory-and-practice/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> <div class="row-card"> <div class="row-card__container"> <div class="row-card__body"> <a class="row-card__heading headline-6 glue-link" href=http://research.google/pubs/grale-designing-networks-for-graph-learning/ > Grale: Designing Networks for Graph Learning </a> <div class="row-card__subheading"> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/jonathanhalcrow/"> Jonathan Jesse Halcrow </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Alexandru Moșoi </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Sam Ruth </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> <a class="row-card__small-link" href="/people/bryanperozzi/"> Bryan Perozzi </a> </div> <div class="row-card__subheading__spacer"></div> <div class="row-card__subheading__item extra-small-text"> Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Association for Computing Machinery (2020), 2523–2532 </div> </div> </div> <div class="row-card__cta headline-6"> <div class="glue-tooltip" data-glue-tooltip-auto-position="false"> <button class="glue-button glue-button--low-emphasis glue-tooltip__trigger" aria-describedby=tooltip-contenthow-can-we-find-the-right-graph-fo tabindex=0 > <span class="js-gt-item-id">Preview</span> </button> <span id="tooltip-contenthow-can-we-find-the-right-graph-fo" class="glue-tooltip__content" role="tooltip"> <span data-tooltip-type="simple"> Preview abstract </span> <span data-tooltip-type="rich"> <span class="glue-tooltip__body">How can we find the right graph for semi-supervised learning? In real world applications, the choice of which edges to use for computation is the first step in any graph learning process. Interestingly, there are often many types of similarity available to choose as the edges between nodes, and the choice of edges can drastically affect the performance of downstream semi-supervised learning systems. However, despite the importance of graph design, most of the literature assumes that the graph is static. In this work, we present Grale, a scalable method we have developed to address the problem of graph design for graphs with billions of nodes. Grale operates by fusing together different measures of (potentially weak) similarity to create a graph which exhibits high task-specific homophily between its nodes. Grale is designed for running on large datasets. We have deployed Grale in more than 20 different industrial settings at Google, including datasets which have tens of billions of nodes, and hundreds of trillions of potential edges to score. By employing locality sensitive hashing techniques, we greatly reduce the number of pairs that need to be scored, allowing us to learn a task specific model and build the associated nearest neighbor graph for such datasets in hours, rather than the days or even weeks that might be required otherwise. We illustrate this through a case study where we examine the application of Grale to an abuse classification problem on YouTube with hundreds of million of items. In this application, we find that Grale detects a large number of malicious actors on top of hard-coded rules and content classifiers, increasing the total recall by 89% over those approaches alone.</span> <a class="glue-button glue-button--low-emphasis" href="http://research.google/pubs/grale-designing-networks-for-graph-learning/" > <span class="js-gt-item-id">View details</span> </a> </span> </span> </div> </div> </div> </div> </div> </section> </div> </div> </section> <section class="offset-two-up --theme-dark both" data-gt-id="offset_two_up" data-gt-component-name="None"> <div class="glue-page glue-grid"> <div class="offset-two-up__left-col glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-3-lg"> <h2 class="offset-two-up__headline headline-3">Highlighted work</h2> </div> <div class="glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-9-lg"> <section class="component-as-block --no-padding-top"> <ul class="card-stack--basic nested-glue-grid-override" data-gt-id="project_basic_card_stack" data-gt-component-name="None"> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="http://research.google/blog/google-research-2022-beyond-algorithmic-advances/" aria-label="" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/parallel-graph-2.width-800.png" alt="distributed-hash-table" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/parallel-graph-2.width-800.png" alt="distributed-hash-table" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> Google Research, 2022 & beyond: Algorithmic advances </span> <div class="glue-card__description glue-spacer-1-top"> This post discusses progress made in several areas in 2022, including scalability, graph algorithms, privacy, market algorithms, and algorithmic foundations. Some of the important points are the development of new algorithms for handling huge datasets, achieving faster running times for graph algorithms including graph building and clustering, and privacy-preserving machine learning. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="http://research.google/blog/massively-parallel-graph-computation-from-theory-to-practice/" aria-label="" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/parallel-graph.width-800.png" alt="Parallel graph" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/parallel-graph.width-800.png" alt="Parallel graph" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> Massively Parallel Graph Computation: From Theory to Practice </span> <div class="glue-card__description glue-spacer-1-top"> Adaptive Massively Parallel Computation (AMPC) augments the theoretical capabilities of MapReduce, providing a pathway to solve many graph problems in fewer computation rounds; the suite of algorithms, which includes algorithms for maximal independent set, maximum matching, connected components and minimum spanning tree, work up to 7x faster than current state-of-the-art approaches. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="http://research.google/blog/balanced-partitioning-and-hierarchical-clustering-at-scale/" aria-label="" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/balanced-partitioning.width-800.jpg" alt="Balanced partitioning" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/balanced-partitioning.width-800.jpg" alt="Balanced partitioning" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> Balanced Partitioning and Hierarchical Clustering at Scale </span> <div class="glue-card__description glue-spacer-1-top"> This post presents the distributed algorithm we developed which is more applicable to large instances. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="http://research.google/blog/innovations-in-graph-representation-learning/" aria-label="" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/innovations-graph.width-800.png" alt="innovations-graph" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/innovations-graph.width-800.png" alt="innovations-graph" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> Innovations in Graph Representation Learning </span> <div class="glue-card__description glue-spacer-1-top"> We share the results of two papers highlighting innovations in the area of graph representation learning: the first paper introduces a novel technique to learn multiple embeddings per node and the second addresses the fundamental problem of hyperparameter tuning in graph embeddings. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="https://gm-neurips-2020.github.io/" aria-label="" target="_blank" rel="noreferrer noopener" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/neurips-2020.width-800.png" alt="Neurips 2020" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/neurips-2020.width-800.png" alt="Neurips 2020" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> Graph Mining & Learning @ NeurIPS 2020 </span> <div class="glue-card__description glue-spacer-1-top"> The Mining and Learning with Graphs at Scale workshop focused on methods for operating on massive information networks: graph-based learning and graph algorithms for a wide range of areas such as detecting fraud and abuse, query clustering and duplication detection, image and multi-modal data analysis, privacy-respecting data mining and recommendation, and experimental design under interference. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="http://research.google/blog/graph-neural-networks-in-tensorflow/" aria-label="" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/graph-neural-network.width-800.png" alt="graph-neural-network" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/graph-neural-network.width-800.png" alt="graph-neural-network" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> Graph Neural Networks in TensorFlow </span> <div class="glue-card__description glue-spacer-1-top"> Graph Neural Networks (GNNs) in TensorFlow (TF-GNN). The post discusses typical GNN architectures, why GNNs are useful and some GNN applications. Most importantly, it announces the release of TensorFlow GNN 1.0—Google's open-source GNN library for TensorFlow. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="http://research.google/blog/robust-graph-neural-networks/" aria-label="" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/robust-neural.width-800.png" alt="robust-neural" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/robust-neural.width-800.png" alt="robust-neural" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> Robust Graph Neural Networks </span> <div class="glue-card__description glue-spacer-1-top"> This blog describes our framework for shift-robust Graph Neural Networks (SR-GNN) that can reduce the influence of biased training data on many GNN architectures. Increasing the robustness of GNN models helps to ensure accurate output in the face of changing data. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="http://research.google/blog/graphworld-advances-in-graph-benchmarking/" aria-label="" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/graphworld.width-800.png" alt="graphworld" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/graphworld.width-800.png" alt="graphworld" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> GraphWorld: Advances in Graph Benchmarking </span> <div class="glue-card__description glue-spacer-1-top"> This blog post introduces GraphWorld, a system that generates synthetic graphs for benchmarking GNNs. GraphWorld allows researchers to explore GNN performance on a wider variety of graphs than was previously possible and identify weaknesses in current GNN Models. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="http://research.google/blog/teaching-old-labels-new-tricks-in-heterogeneous-graphs/" aria-label="" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/knowledge-transfer-network.width-800.png" alt="knowledge-transfer-network" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/knowledge-transfer-network.width-800.png" alt="knowledge-transfer-network" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> Teaching old labels new tricks in heterogeneous graphs </span> <div class="glue-card__description glue-spacer-1-top"> Complex data struggles with limited labels for certain types, hurting HGNN performance. Our Knowledge Transfer Network (KTN) tackles this by finding connections between node types. KTN transfers knowledge from well-labeled nodes to those with few labels, allowing HGNNs to learn better representations for all data points. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="http://research.google/blog/advancements-in-machine-learning-for-machine-learning/" aria-label="" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/graph-training.width-800.png" alt="graph-training" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/graph-training.width-800.png" alt="graph-training" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> Advancements in machine learning for machine learning </span> <div class="glue-card__description glue-spacer-1-top"> In this blog post, we present exciting advancements in machine learning to improve machine learning (ML 4 ML)! In particular, we show how we use Graph Neural Networks to improve the efficiency of ML workloads by optimizing the choices made by the ML Compiler. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="http://research.google/blog/differentially-private-clustering-for-large-scale-datasets/" aria-label="" > <div class="glue-card__inner"> <picture class="glue-card__asset play-pause-size-override"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/private-clustering.width-800.png" alt="private-clustering" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/private-clustering.width-800.png" alt="private-clustering" loading="lazy" /> </picture> <div class="glue-card__content --no-media"> <span class="headline-5 js-gt-item-id"> Differentially private clustering for large-scale datasets </span> <div class="glue-card__description glue-spacer-1-top"> This blog highlights advancements in privacy-preserving clustering: 1) a novel ICML 2023 algorithm and 2) open-source scalable k-means code. We also discuss applying these techniques to inform public health via COVID Vaccine Insights. </div> </div> <div class="glue-card__cta"> <span class="glue-button glue-spacer-1-top glue-button--low-emphasis"> Learn More </span> </div> </div> </a> </li> </ul> </section> </div> </div> </section> <section class="offset-two-up --theme-light both" data-gt-id="offset_two_up" data-gt-component-name="None"> <div class="glue-page glue-grid"> <div class="offset-two-up__left-col glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-3-lg"> <h2 class="offset-two-up__headline headline-3">Some of our locations</h2> </div> <div class="glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-9-lg"> <section class="component-as-block --no-padding-top"> <div class="card-stack--basic" data-gt-id="basic_card_stack" data-gt-component-name="None"> <ul class="nested-glue-grid-override"> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="https://www.google.com/about/careers/applications/locations/atlanta/" aria-label="" target="_blank" rel="noreferrer noopener" > <div class="glue-card__inner"> <div data-gt-id="media" data-gt-component-name="None">   <picture class="glue-card__asset play-pause-size-override media__image"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/center-atlanta.width-800.jpg" alt="Center Atlanta" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/center-atlanta.width-800.jpg" alt="Center Atlanta" loading="lazy" /> </picture> </div> <div class="glue-card__content "> <span class="headline-5 js-gt-item-id"> Atlanta </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="https://www.google.com/about/careers/applications/locations/cambridge/" aria-label="" target="_blank" rel="noreferrer noopener" > <div class="glue-card__inner"> <div data-gt-id="media" data-gt-component-name="None">   <picture class="glue-card__asset play-pause-size-override media__image"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/center-cambridge.width-800.jpg" alt="Center Cambridge" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/center-cambridge.width-800.jpg" alt="Center Cambridge" loading="lazy" /> </picture> </div> <div class="glue-card__content "> <span class="headline-5 js-gt-item-id"> Cambridge </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="https://www.google.com/about/careers/applications/locations/new-york/" aria-label="" target="_blank" rel="noreferrer noopener" > <div class="glue-card__inner"> <div data-gt-id="media" data-gt-component-name="None">   <picture class="glue-card__asset play-pause-size-override media__image"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/NY.width-800.jpg" alt="NY" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/NY.width-800.jpg" alt="NY" loading="lazy" /> </picture> </div> <div class="glue-card__content "> <span class="headline-5 js-gt-item-id"> New York </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="https://www.google.com/about/careers/applications/locations/san-francisco/" aria-label="" target="_blank" rel="noreferrer noopener" > <div class="glue-card__inner"> <div data-gt-id="media" data-gt-component-name="None">   <picture class="glue-card__asset play-pause-size-override media__image"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/SF.width-800.jpg" alt="SF" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/SF.width-800.jpg" alt="SF" loading="lazy" /> </picture> </div> <div class="glue-card__content "> <span class="headline-5 js-gt-item-id"> San Francisco Bay Area </span> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-4-md glue-grid__col--span-4-sm"> <a class="glue-card not-glue " href="https://www.google.com/about/careers/applications/locations/zurich" aria-label="" target="_blank" rel="noreferrer noopener" > <div class="glue-card__inner"> <div data-gt-id="media" data-gt-component-name="None">   <picture class="glue-card__asset play-pause-size-override media__image"> <source media="(min-width: 768px)" srcset="https://storage.googleapis.com/gweb-research2023-media/images/Zurich.width-800.jpg" alt="Zurich" /> <img src="https://storage.googleapis.com/gweb-research2023-media/images/Zurich.width-800.jpg" alt="Zurich" loading="lazy" /> </picture> </div> <div class="glue-card__content "> <span class="headline-5 js-gt-item-id"> Zurich </span> </div> </div> </a> </li> </ul> </div> </section> </div> </div> </section> <section class="offset-two-up --theme-dark both" data-gt-id="offset_two_up" data-gt-component-name="None"> <div class="glue-page glue-grid"> <div class="offset-two-up__left-col glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-3-lg"> <h2 class="offset-two-up__headline headline-3">Some of our people</h2> </div> <div class="glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-12-md glue-grid__col--span-9-lg"> <section class="component-as-block --no-padding-top"> <div class="js-show-more-list" data-show-more-items-per-view="12" data-gt-id="people_card_stack" data-show-more-hidden-class="--hidden" data-gt-component-name="None"> <ul class="card-stack--people glue-grid" > <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/alessandroepasto/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/3444.png" alt="Alessandro Epasto" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Alessandro Epasto</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/allanheydon/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/5766.png" alt="Allan Heydon" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Allan Heydon</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Machine Intelligence</li> <li class="glue-labels small-text">Software Engineering</li> <li class="glue-labels small-text">Software Systems</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/107839/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/7756.png" alt="Anton Tsitsulin" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Anton Tsitsulin</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/arjungopalan/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/5729.png" alt="Arjun Gopalan" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Arjun Gopalan</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/108300/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/7716.png" alt="Bahare Fatemi" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Bahare Fatemi</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Machine Perception</li> <li class="glue-labels small-text">Natural Language Processing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/107936/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/6641.png" alt="Brandon Asher Mayer" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Brandon Asher Mayer</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> <li class="glue-labels small-text">Machine Intelligence</li> <li class="glue-labels small-text">Machine Perception</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/bryanperozzi/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/3525.png" alt="Bryan Perozzi" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Bryan Perozzi</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/cjcarey/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/6642.png" alt="CJ Carey" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">CJ Carey</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/davideisenstat/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/7720.png" alt="David Eisenstat" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">David Eisenstat</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/106375/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="/gr/static/assets/images/missing-person-thumbnail.png" alt=""> </picture> <div class="glue-card__content"> <p class="glue-headline body">Dustin Zelle</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/108366/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/7058.png" alt="Goran Žužić" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Goran Žužić</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item "> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/hendrikfichtenberger/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="/gr/static/assets/images/missing-person-thumbnail.png" alt=""> </picture> <div class="glue-card__content"> <p class="glue-headline body">Hendrik Fichtenberger</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/jasonlee/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/7746.png" alt="Jason Lee" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Jason Lee</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/johannesgasteigernklicpera/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/7162.png" alt="Johannes Gasteiger, né Klicpera" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Johannes Gasteiger, né Klicpera</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/jonathanhalcrow/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/6088.png" alt="Jonathan Halcrow" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Jonathan Halcrow</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/106559/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/5141.png" alt="Kevin Aydin" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Kevin Aydin</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/105517/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/4097.png" alt="Jakub Łącki" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Jakub Łącki</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/laxmandhulipala/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/7745.png" alt="Laxman Dhulipala" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Laxman Dhulipala</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/linchen/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="/gr/static/assets/images/missing-person-thumbnail.png" alt=""> </picture> <div class="glue-card__content"> <p class="glue-headline body">Lin Chen</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/106910/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/5498.png" alt="Matthew Fahrbach" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Matthew Fahrbach</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/bateni/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/39.png" alt="Mohammadhossein Bateni" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Mohammadhossein Bateni</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/nikosparotsidis/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/7765.png" alt="Nikos Parotsidis" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Nikos Parotsidis</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/108328/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="/gr/static/assets/images/missing-person-thumbnail.png" alt=""> </picture> <div class="glue-card__content"> <p class="glue-headline body">Peilin Zhong</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/107587/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/6299.png" alt="Rajesh Jayaram" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Rajesh Jayaram</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/104861/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/3515.png" alt="Sami Abu-El-Haija" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Sami Abu-El-Haija</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Machine Perception</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/sasantavakkol/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/5758.png" alt="Sasan Tavakkol" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Sasan Tavakkol</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/siddharthavisveswarajayanti/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/7052.png" alt="Siddhartha Visveswara Jayanti" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Siddhartha Visveswara Jayanti</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/silviolattanzi/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/305.png" alt="Silvio Lattanzi" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Silvio Lattanzi</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/104854/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="/gr/static/assets/images/missing-person-thumbnail.png" alt=""> </picture> <div class="glue-card__content"> <p class="glue-headline body">Gang (Thomas) Fu</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> <li class="glue-labels small-text">Machine Learning</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/mirrokni/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/904.png" alt="Vahab S. Mirrokni" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Vahab S. Mirrokni</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Data Mining and Modeling</li> <li class="glue-labels small-text">Distributed Systems and Parallel Computing</li> <li class="glue-labels small-text">Algorithms and Theory</li> </ul> </div> </div> </a> </li> <li class="glue-grid__col glue-grid__col--span-3-lg glue-grid__col--span-4-md glue-grid__col--span-4-sm js-show-more-list__item --hidden"> <a class="glue-card not-glue glue-card--people" href="http://research.google/people/107320/"> <div class="glue-card__inner"> <picture class="glue-card__asset"> <img src="https://storage.googleapis.com/gweb-research2023-media/pubtools/5972.png" alt="Vincent Pierre Cohen-addad" loading="lazy"> </picture> <div class="glue-card__content"> <p class="glue-headline body">Vincent Pierre Cohen-addad</p> <ul class="glue-no-bullet" role="list"> <li class="glue-labels small-text">Algorithms and Theory</li> <li class="glue-labels small-text">Machine Intelligence</li> </ul> </div> </div> </a> </li> </ul> <div class="card-stack--people__button-container"> <button class="glue-button glue-button--medium-emphasis glue-button--reversed js-show-more-list__button" > <span class="js-gt-item-id">Load more</span> </button> </div> </div> </section> </div> </div> </section> <section class="banner --theme-light" data-gt-id="banner" data-gt-component-name="None"> <div class="banner__wrapper glue-page glue-grid"> <div class="banner__copy glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-6-md"> <h2 class="banner__headline headline-3">Join us</h2> <p class="banner__body-copy body">We're always looking for more talented, passionate people.</p> <a class="glue-button glue-button--medium-emphasis" href="http://research.google/careers/" > <span class="js-gt-item-id">See opportunities</span> </a> </div> <div class="glue-grid__col glue-grid__col--span-0-sm glue-grid__col--span-1"></div> <div class="banner__image glue-grid__col glue-grid__col--span-4-sm glue-grid__col--span-5-md"> <img src="https://storage.googleapis.com/gweb-research2023-media/images/Careers.original.jpg" alt="Careers" /> </div> </div> </section> </main> <footer class="glue-footer"> <div class="glue-page"> <section class="glue-social"> <div class="glue-social__group glue-social--monochrome"> <p class="glue-social__title glue-social__title--inline"> Follow us </p> <nav class="js-gt-follow-us-wrapper" aria-label="Social media links"> <ul class="glue-social__list" role="list"> <li class="glue-social__item"> <a class="glue-social__link" href="https://twitter.com/GoogleAI" title="Follow us on x" target="_blank" rel="noopener" data-gt-method="x"" > <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--social glue-icon--24px"> <use href="/gr/static/assets/icons/twitter-x.svg#twitter-x"></use> </svg> </a> </li> <li class="glue-social__item"> <a class="glue-social__link" href="https://www.linkedin.com/showcase/googleresearch/" title="Follow us on linkedin" target="_blank" rel="noopener" data-gt-method="linkedin"" > <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--social glue-icon--24px"> <use href="/gr/static/assets/icons/glue-icons.svg#post-linkedin"></use> </svg> </a> </li> <li class="glue-social__item"> <a class="glue-social__link" href="https://www.youtube.com/c/GoogleResearch" title="Follow us on youtube" target="_blank" rel="noopener" data-gt-method="youtube"" > <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--social glue-icon--24px"> <use href="/gr/static/assets/icons/glue-icons.svg#video-youtube"></use> </svg> </a> </li> <li class="glue-social__item"> <a class="glue-social__link" href="https://github.com/google-research" title="Follow us on github" target="_blank" rel="noopener" data-gt-method="github"" > <svg role="presentation" aria-hidden="true" class="glue-icon glue-icon--social glue-icon--24px"> <use href="/gr/static/assets/icons/github.svg#github"></use> </svg> </a> </li> </ul> </nav> </div> </section> </div> <div class="glue-fullbleed"></div> <section class="glue-page"> <nav class="glue-footer__global" aria-label="Footer resource links"> <div class="glue-footer__logo"> <a href="https://www.google.com" title="Google" class="glue-footer__link"> <svg role="presentation" aria-hidden="true" class="glue-icon glue-footer__logo-img"> <use href="/gr/static/assets/icons/glue-icons.svg#google-solid-logo"></use> </svg> </a> </div> <ul class="glue-footer__global-links glue-no-bullet js-gt-global-nav-wrapper" role="list"> <li class="glue-footer__global-links-list-item" data-gt-primary="About Google"> <a class="glue-footer__link" href="https://about.google/" target="_blank" rel="noopener"> About Google </a> </li> <li class="glue-footer__global-links-list-item" data-gt-primary="Google Products"> <a class="glue-footer__link" href="https://about.google/intl/en/products/" target="_blank" rel="noopener"> Google Products </a> </li> <li class="glue-footer__global-links-list-item" data-gt-primary="Privacy"> <a class="glue-footer__link" href="https://policies.google.com/privacy" target="_blank" rel="noopener"> Privacy </a> </li> <li class="glue-footer__global-links-list-item" data-gt-primary="Terms"> <a class="glue-footer__link" href="https://policies.google.com/terms" target="_blank" rel="noopener"> Terms </a> </li> </ul> <ul class="glue-footer__global-links glue-footer__global-links--extra glue-no-bullet" role="list"> <li class="glue-footer__global-links-list-item glue-footer__global-links-list-item--extra"> <a class="glue-footer__link" href="https://support.google.com/?hl=en"> <svg role="presentation" aria-hidden="true" aria-hidden="true" class="glue-icon glue-icon--24px glue-icon--footer-help"> <use href="/gr/static/assets/icons/glue-icons.svg#help"></use> </svg> Help </a> </li> <li class="glue-footer__global-links-list-item glue-footer__global-links-list-item--extra"> <button class="glue-footer__link google-feedback js-feedback-button" href="" data-product-id="5137383" > Submit feedback </button> </li> </ul> </nav> </section> </footer> <script src="https://www.gstatic.com/glue/v27_1/material-components-web.min.js"></script> <script src="https://www.youtube.com/player_api"></script> <script type="text/javascript" src="/gr/static/js/googleresearch.js?id=b70549917812130af912601ad763f13e"></script> <script type="text/javascript" src="https://support.google.com/inapp/api.js"></script> <script src="https://www.gstatic.com/glue/cookienotificationbar/cookienotificationbar.min.js" data-glue-cookie-notification-bar-category="2B"> </script> </body> </html>

CINXE.COM

Graph mining