{"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/manifold-restricted-interventional-shapley","title":"Manifold Restricted Interventional Shapley Values","arxiv_id":"2301.04041","date":"2023-01-10","proceeding":null,"authors":["Muhammad Faaiz Taufiq","Patrick Blöbaum","Lenon Minorics"],"abstract":"Shapley values are model-agnostic methods for explaining model predictions. Many commonly used methods of computing Shapley values, known as off-manifold methods, rely on model evaluations on out-of-distribution input samples. Consequently, explanations obtained are sensitive to model behaviour outside the data distribution, which may be irrelevant for all practical purposes. While on-manifold methods have been proposed which do not suffer from this problem, we show that such methods are overly dependent on the input data distribution, and therefore result in unintuitive and misleading explanations. To circumvent these problems, we propose ManifoldShap, which respects the model's domain of validity by restricting model evaluations to the data manifold. We show, theoretically and empirically, that ManifoldShap is robust to off-manifold perturbations of the model and leads to more accurate and intuitive explanations than existing state-of-the-art Shapley methods.","url_abs":"https://arxiv.org/abs/2301.04041v2","url_pdf":"https://arxiv.org/pdf/2301.04041v2.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":"manifold-restricted-interventional-shapley","repo_url":"https://github.com/amazon-science/manifold-restricted-shapley","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.04041","atlas_url":"https://app.syntology.ai/?focus=2301.04041","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.04041"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/amazon-science/manifold-restricted-shapley","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"014bd20a18d0b608","entry":"generate_data_for_manifold_classifier","repo":"amazon-science/manifold-restricted-shapley","repo_kind":"official","path":"OODShapley/manifold_classifier/data_generator.py","file_url":"https://github.com/amazon-science/manifold-restricted-shapley/blob/HEAD/OODShapley/manifold_classifier/data_generator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"014bd20a18d0b608"}},{"code_sha256_prefix":"3eb0b8635b293036","entry":"generate_perturbed_data","repo":"amazon-science/manifold-restricted-shapley","repo_kind":"official","path":"OODShapley/off_manifold_perturbation/data_generator.py","file_url":"https://github.com/amazon-science/manifold-restricted-shapley/blob/HEAD/OODShapley/off_manifold_perturbation/data_generator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3eb0b8635b293036"}},{"code_sha256_prefix":"b81962c00d030b2f","entry":"generate_perturbed_data_wrt_density","repo":"amazon-science/manifold-restricted-shapley","repo_kind":"official","path":"OODShapley/off_manifold_perturbation/data_generator.py","file_url":"https://github.com/amazon-science/manifold-restricted-shapley/blob/HEAD/OODShapley/off_manifold_perturbation/data_generator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b81962c00d030b2f"}},{"code_sha256_prefix":"dc7d3925f36aa64d","entry":"fit_classifier","repo":"amazon-science/manifold-restricted-shapley","repo_kind":"official","path":"OODShapley/manifold_classifier/train_classifier.py","file_url":"https://github.com/amazon-science/manifold-restricted-shapley/blob/HEAD/OODShapley/manifold_classifier/train_classifier.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dc7d3925f36aa64d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}