{"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/fast-axiomatic-attribution-for-neural","title":"Fast Axiomatic Attribution for Neural Networks","arxiv_id":"2111.07668","date":"2021-11-15","proceeding":"NeurIPS 2021 12","authors":["Robin Hesse","Simone Schaub-Meyer","Stefan Roth"],"abstract":"Mitigating the dependence on spurious correlations present in the training dataset is a quickly emerging and important topic of deep learning. Recent approaches include priors on the feature attribution of a deep neural network (DNN) into the training process to reduce the dependence on unwanted features. However, until now one needed to trade off high-quality attributions, satisfying desirable axioms, against the time required to compute them. This in turn either led to long training times or ineffective attribution priors. In this work, we break this trade-off by considering a special class of efficiently axiomatically attributable DNNs for which an axiomatic feature attribution can be computed with only a single forward/backward pass. We formally prove that nonnegatively homogeneous DNNs, here termed $\\mathcal{X}$-DNNs, are efficiently axiomatically attributable and show that they can be effortlessly constructed from a wide range of regular DNNs by simply removing the bias term of each layer. Various experiments demonstrate the advantages of $\\mathcal{X}$-DNNs, beating state-of-the-art generic attribution methods on regular DNNs for training with attribution priors.","url_abs":"https://arxiv.org/abs/2111.07668v1","url_pdf":"https://arxiv.org/pdf/2111.07668v1.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":"fast-axiomatic-attribution-for-neural","repo_url":"https://github.com/visinf/fast-axiomatic-attribution","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.07668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07668"}},"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/visinf/fast-axiomatic-attribution","reach":null}],"summary":{"ran":1,"ran_fixture":1,"ran_draft_wrong":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"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":1,"samples":[{"code_sha256_prefix":"ba320595cb4b765b","entry":"AttributionPriorExplainer","repo":"visinf/fast-axiomatic-attribution","repo_kind":"official","path":"imagenet/utils/expected_gradients.py","file_url":"https://github.com/visinf/fast-axiomatic-attribution/blob/HEAD/imagenet/utils/expected_gradients.py","link_basis":"first_harvest_node","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":"ba320595cb4b765b"}},{"code_sha256_prefix":"131a82fd65128218","entry":"accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"131a82fd65128218"}},{"code_sha256_prefix":"c07c10d6dabb86be","entry":"gather_nd","repo":"visinf/fast-axiomatic-attribution","repo_kind":"official","path":"imagenet/utils/expected_gradients.py","file_url":"https://github.com/visinf/fast-axiomatic-attribution/blob/HEAD/imagenet/utils/expected_gradients.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c07c10d6dabb86be"}},{"code_sha256_prefix":"5c22680084c0ea6f","entry":"validate","repo":"visinf/fast-axiomatic-attribution","repo_kind":"official","path":"imagenet/train_alexnet_vgg.py","file_url":"https://github.com/visinf/fast-axiomatic-attribution/blob/HEAD/imagenet/train_alexnet_vgg.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c22680084c0ea6f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}