{"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/provably-better-explanations-with-optimized","title":"Provably Better Explanations with Optimized Aggregation of Feature Attributions","arxiv_id":"2406.05090","date":"2024-06-07","proceeding":null,"authors":["Thomas Decker","Ananta R. Bhattarai","Jindong Gu","Volker Tresp","Florian Buettner"],"abstract":"Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous techniques available, individual methods often produce inconsistent and unstable results, putting their overall reliability into question. In this work, we aim to systematically improve the quality of feature attributions by combining multiple explanations across distinct methods or their variations. For this purpose, we propose a novel approach to derive optimal convex combinations of feature attributions that yield provable improvements of desired quality criteria such as robustness or faithfulness to the model behavior. Through extensive experiments involving various model architectures and popular feature attribution techniques, we demonstrate that our combination strategy consistently outperforms individual methods and existing baselines.","url_abs":"https://arxiv.org/abs/2406.05090v1","url_pdf":"https://arxiv.org/pdf/2406.05090v1.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":[],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.05090","atlas_url":"https://app.syntology.ai/?focus=2406.05090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05090"}},"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":"deterministic:regex_extraction","url":"https://github.com/thomdeck/aggopt","reach":null}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"found_in_text":{"samples":5,"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":"0bd64df758577d9d","entry":"Model","repo":"thomdeck/aggopt","repo_kind":"found_in_text","path":"src/agg_explainers.py","file_url":"https://github.com/thomdeck/aggopt/blob/HEAD/src/agg_explainers.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":"0bd64df758577d9d"}},{"code_sha256_prefix":"78856bfd8d57a49f","entry":"AGGfaith_explainer","repo":"thomdeck/aggopt","repo_kind":"found_in_text","path":"src/agg_explainers.py","file_url":"https://github.com/thomdeck/aggopt/blob/HEAD/src/agg_explainers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78856bfd8d57a49f"}},{"code_sha256_prefix":"3fc994bbed5477b9","entry":"AGGopt_explainer","repo":"thomdeck/aggopt","repo_kind":"found_in_text","path":"src/agg_explainers.py","file_url":"https://github.com/thomdeck/aggopt/blob/HEAD/src/agg_explainers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3fc994bbed5477b9"}},{"code_sha256_prefix":"3d3408b63b72ba0c","entry":"agg_explainer","repo":"thomdeck/aggopt","repo_kind":"found_in_text","path":"src/agg_explainers.py","file_url":"https://github.com/thomdeck/aggopt/blob/HEAD/src/agg_explainers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d3408b63b72ba0c"}},{"code_sha256_prefix":"c4aea986f3c072f6","entry":"explainer","repo":"thomdeck/aggopt","repo_kind":"found_in_text","path":"src/agg_explainers.py","file_url":"https://github.com/thomdeck/aggopt/blob/HEAD/src/agg_explainers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c4aea986f3c072f6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}