{"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-the-robustness-of-global-feature-effect","title":"On the Robustness of Global Feature Effect Explanations","arxiv_id":"2406.09069","date":"2024-06-13","proceeding":null,"authors":["Hubert Baniecki","Giuseppe Casalicchio","Bernd Bischl","Przemyslaw Biecek"],"abstract":"We study the robustness of global post-hoc explanations for predictive models trained on tabular data. Effects of predictor features in black-box supervised learning are an essential diagnostic tool for model debugging and scientific discovery in applied sciences. However, how vulnerable they are to data and model perturbations remains an open research question. We introduce several theoretical bounds for evaluating the robustness of partial dependence plots and accumulated local effects. Our experimental results with synthetic and real-world datasets quantify the gap between the best and worst-case scenarios of (mis)interpreting machine learning predictions globally.","url_abs":"https://arxiv.org/abs/2406.09069v1","url_pdf":"https://arxiv.org/pdf/2406.09069v1.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-the-robustness-of-global-feature-effect","repo_url":"https://github.com/hbaniecki/robust-feature-effects","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"scientific-discovery","task_name":"scientific discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.09069","atlas_url":"https://app.syntology.ai/?focus=2406.09069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09069"}},"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/hbaniecki/robust-feature-effects","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"6d5caa9f8bb4b5f7","entry":"check_early_stopping","repo":"hbaniecki/robust-feature-effects","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/hbaniecki/robust-feature-effects/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d5caa9f8bb4b5f7"}},{"code_sha256_prefix":"3b200194bc918ad6","entry":"distance_values","repo":"hbaniecki/robust-feature-effects","repo_kind":"official","path":"src/loss.py","file_url":"https://github.com/hbaniecki/robust-feature-effects/blob/HEAD/src/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b200194bc918ad6"}},{"code_sha256_prefix":"831e0df4b6f765d1","entry":"loss","repo":"hbaniecki/robust-feature-effects","repo_kind":"official","path":"src/loss.py","file_url":"https://github.com/hbaniecki/robust-feature-effects/blob/HEAD/src/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"831e0df4b6f765d1"}},{"code_sha256_prefix":"70b16a7fc8254617","entry":"loss_pop","repo":"hbaniecki/robust-feature-effects","repo_kind":"official","path":"src/loss.py","file_url":"https://github.com/hbaniecki/robust-feature-effects/blob/HEAD/src/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70b16a7fc8254617"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}