{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-counterfactual-networks-with-propensity","title":"Deep Counterfactual Networks with Propensity-Dropout","arxiv_id":"1706.05966","date":"2017-06-19","proceeding":null,"authors":["Ahmed M. Alaa","Michael Weisz","Mihaela van der Schaar"],"abstract":"We propose a novel approach for inferring the individualized causal effects\nof a treatment (intervention) from observational data. Our approach\nconceptualizes causal inference as a multitask learning problem; we model a\nsubject's potential outcomes using a deep multitask network with a set of\nshared layers among the factual and counterfactual outcomes, and a set of\noutcome-specific layers. The impact of selection bias in the observational data\nis alleviated via a propensity-dropout regularization scheme, in which the\nnetwork is thinned for every training example via a dropout probability that\ndepends on the associated propensity score. The network is trained in\nalternating phases, where in each phase we use the training examples of one of\nthe two potential outcomes (treated and control populations) to update the\nweights of the shared layers and the respective outcome-specific layers.\nExperiments conducted on data based on a real-world observational study show\nthat our algorithm outperforms the state-of-the-art.","url_abs":"http://arxiv.org/abs/1706.05966v1","url_pdf":"http://arxiv.org/pdf/1706.05966v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-counterfactual-networks-with-propensity","repo_url":"https://github.com/Shantanu48114860/Deep-Counterfactual-Networks-with-Propensity-Dropout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"causal-inference","task_name":"Causal Inference"},{"task_slug":"selection-bias","task_name":"Selection bias"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"causal-inference","method_name":"Causal inference"},{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.05966","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}