{"id":788789,"date":"2021-10-26T21:59:44","date_gmt":"2021-10-27T04:59:44","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=788789"},"modified":"2021-11-25T18:59:46","modified_gmt":"2021-11-26T02:59:46","slug":"causal-learning-inference","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/causal-learning-inference\/","title":{"rendered":"Causal Learning-Inference"},"content":{"rendered":"<section class=\"mb-3 moray-highlight\">\n\t<div class=\"card-img-overlay mx-lg-0\">\n\t\t<div class=\"card-background bg-gray-200 has-background- card-background--full-bleed\">\n\t\t\t\t\t<\/div>\n\t\t<!-- Foreground -->\n\t\t<div class=\"card-foreground d-flex mt-md-n5 my-lg-5 px-g px-lg-0\">\n\t\t\t<!-- Container -->\n\t\t\t<div class=\"container d-flex mt-md-n5 my-lg-5 align-self-center\">\n\t\t\t\t<!-- Card wrapper -->\n\t\t\t\t<div class=\"w-100 w-lg-col-5\">\n\t\t\t\t\t<!-- Card -->\n\t\t\t\t\t<div class=\"card material-md-card py-5 px-md-5\">\n\t\t\t\t\t\t<div class=\"card-body \">\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n<h1 id=\"causal-learning-inference\">Causal Learning-Inference<\/h1>\n\n\n\n<p><\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n<p>Current AI models can learn spurious correlation during data-fitting process, which can incur the failure of generalizing to new unseen domains. To resolve this problem, we resort to causal inference, with the expectation to learning causal relation that is invariant and stable in any environment. Our departure to the traditional transfer learning lies in the causal perspective, that is, our goal is discovering and exploiting causal relations for out-of-distribution generalization. We will apply our models to safety-critical tasks, such as healthcare and security.<\/p>\n\n\n\n\n\n<ul class=\"wp-block-list\"><li>Sun, Xinwei, Botong Wu, Xiangyu Zheng, Chang Liu, Wei Chen, Tao Qin, and Tie-Yan Liu. &#8220;Recovering Latent Causal Factor for Generalization to Distributional Shifts.&#8221; In&nbsp;<em>Thirty-Fifth Conference on Neural Information Processing Systems<\/em>. 2021.<\/li><li>Liu, Chang, Xinwei Sun, Jindong Wang, Haoyue Tang, Tao Li, Tao Qin, Wei Chen, and Tie-Yan Liu. &#8220;Learning causal semantic representation for out-of-distribution prediction.&#8221; In&nbsp;<em>Thirty-Fifth Conference on Neural Information Processing Systems<\/em>. 2021.<\/li><li>Zheng, Xiangyu, Xinwei Sun, Wei Chen, and Tie-Yan Liu. &#8220;Causally Invariant Predictor with Shift-Robustness.&#8221;&nbsp;<em>arXiv preprint arXiv:2107.01876<\/em>&nbsp;(2021).<\/li><\/ul>\n\n\n","protected":false},"excerpt":{"rendered":"<p>Current AI models can learn spurious correlation during data-fitting process, which can incur the failure of generalizing to new unseen domains. To resolve this problem, we resort to causal inference, with the expectation to learning causal relation that is invariant and stable in any environment. Our departure to the traditional transfer learning lies in the [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-788789","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[825643,901137,941538],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Chang Liu","user_id":39889,"people_section":"Section name 0","alias":"changliu"}],"msr_research_lab":[199560],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/788789"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/788789\/revisions"}],"predecessor-version":[{"id":799918,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/788789\/revisions\/799918"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=788789"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=788789"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=788789"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=788789"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=788789"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}