{"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/learning-to-explain-an-information-theoretic","title":"Learning to Explain: An Information-Theoretic Perspective on Model Interpretation","arxiv_id":"1802.07814","date":"2018-02-21","proceeding":"ICML 2018 7","authors":["Jianbo Chen","Le Song","Martin J. Wainwright","Michael. I. Jordan"],"abstract":"We introduce instancewise feature selection as a methodology for model\ninterpretation. Our method is based on learning a function to extract a subset\nof features that are most informative for each given example. This feature\nselector is trained to maximize the mutual information between selected\nfeatures and the response variable, where the conditional distribution of the\nresponse variable given the input is the model to be explained. We develop an\nefficient variational approximation to the mutual information, and show the\neffectiveness of our method on a variety of synthetic and real data sets using\nboth quantitative metrics and human evaluation.","url_abs":"http://arxiv.org/abs/1802.07814v2","url_pdf":"http://arxiv.org/pdf/1802.07814v2.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":"learning-to-explain-an-information-theoretic","repo_url":"https://github.com/Jianbo-Lab/L2X","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-to-explain-an-information-theoretic","repo_url":"https://github.com/vikua/l2x","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-to-explain-an-information-theoretic","repo_url":"https://github.com/willisk/VIBI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1802.07814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.07814"}},"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/Jianbo-Lab/L2X","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/willisk/VIBI","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vikua/l2x","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"7bf375c6593e3c2c","entry":"compute_median_rank","repo":"Jianbo-Lab/L2X","repo_kind":"official","path":"synthetic/explain.py","file_url":"https://github.com/Jianbo-Lab/L2X/blob/HEAD/synthetic/explain.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7bf375c6593e3c2c"}},{"code_sha256_prefix":"19ec5a639f83508e","entry":"create_rank","repo":"Jianbo-Lab/L2X","repo_kind":"official","path":"synthetic/explain.py","file_url":"https://github.com/Jianbo-Lab/L2X/blob/HEAD/synthetic/explain.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"19ec5a639f83508e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}