{"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/on-inductive-biases-for-heterogeneous","title":"On Inductive Biases for Heterogeneous Treatment Effect Estimation","arxiv_id":"2106.03765","date":"2021-06-07","proceeding":"NeurIPS 2021 12","authors":["Alicia Curth","Mihaela van der Schaar"],"abstract":"We investigate how to exploit structural similarities of an individual's potential outcomes (POs) under different treatments to obtain better estimates of conditional average treatment effects in finite samples. Especially when it is unknown whether a treatment has an effect at all, it is natural to hypothesize that the POs are similar - yet, some existing strategies for treatment effect estimation employ regularization schemes that implicitly encourage heterogeneity even when it does not exist and fail to fully make use of shared structure. In this paper, we investigate and compare three end-to-end learning strategies to overcome this problem - based on regularization, reparametrization and a flexible multi-task architecture - each encoding inductive bias favoring shared behavior across POs. To build understanding of their relative strengths, we implement all strategies using neural networks and conduct a wide range of semi-synthetic experiments. We observe that all three approaches can lead to substantial improvements upon numerous baselines and gain insight into performance differences across various experimental settings.","url_abs":"https://arxiv.org/abs/2106.03765v2","url_pdf":"https://arxiv.org/pdf/2106.03765v2.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":"on-inductive-biases-for-heterogeneous","repo_url":"https://github.com/AliciaCurth/CATENets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"on-inductive-biases-for-heterogeneous","repo_url":"https://github.com/nlokeshiisc/pairnet_release","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"heterogeneous-treatment-effect-estimation","task_name":"Heterogeneous Treatment Effect Estimation"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"pos","task_name":"POS"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.03765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03765"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nlokeshiisc/pairnet_release","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AliciaCurth/CATENets","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f76e1a21707c2931","entry":"dict_to_str","repo":"nlokeshiisc/pairnet_release","repo_kind":"listed","path":"experiments/experiments_benchmarks_NeurIPS21/ihdp_experiments_catenets.py","file_url":"https://github.com/nlokeshiisc/pairnet_release/blob/HEAD/experiments/experiments_benchmarks_NeurIPS21/ihdp_experiments_catenets.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f76e1a21707c2931"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}