{"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/interpretations-are-useful-penalizing","title":"Interpretations are useful: penalizing explanations to align neural networks with prior knowledge","arxiv_id":"1909.13584","date":"2019-09-30","proceeding":"ICML 2020 1","authors":["Laura Rieger","Chandan Singh","W. James Murdoch","Bin Yu"],"abstract":"For an explanation of a deep learning model to be effective, it must provide both insight into a model and suggest a corresponding action in order to achieve some objective. Too often, the litany of proposed explainable deep learning methods stop at the first step, providing practitioners with insight into a model, but no way to act on it. In this paper, we propose contextual decomposition explanation penalization (CDEP), a method which enables practitioners to leverage existing explanation methods in order to increase the predictive accuracy of deep learning models. In particular, when shown that a model has incorrectly assigned importance to some features, CDEP enables practitioners to correct these errors by directly regularizing the provided explanations. Using explanations provided by contextual decomposition (CD) (Murdoch et al., 2018), we demonstrate the ability of our method to increase performance on an array of toy and real datasets.","url_abs":"https://arxiv.org/abs/1909.13584v4","url_pdf":"https://arxiv.org/pdf/1909.13584v4.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":"interpretations-are-useful-penalizing","repo_url":"https://github.com/laura-rieger/deep-explanation-penalization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"interpretations-are-useful-penalizing","repo_url":"https://github.com/csinva/local-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"interpretations-are-useful-penalizing","repo_url":"https://github.com/csinva/transformation-importance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"interpretations-are-useful-penalizing","repo_url":"https://dagshub.com/ShaileshSridhar2403/Re-CDEP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"cdep","method_name":"CDEP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.13584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.13584"}},"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/csinva/transformation-importance","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://dagshub.com/ShaileshSridhar2403/Re-CDEP","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/csinva/local-vae","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/laura-rieger/deep-explanation-penalization","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":1,"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":"ef0809bca2dd8069","entry":"mean","repo":"csinva/local-vae","repo_kind":"listed","path":"lib/disentangling-vae/disvae/training.py","file_url":"https://github.com/csinva/local-vae/blob/HEAD/lib/disentangling-vae/disvae/training.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef0809bca2dd8069"}},{"code_sha256_prefix":"47f0c1095f604511","entry":"propagate_conv_linear","repo":"laura-rieger/deep-explanation-penalization","repo_kind":"official","path":"src/cd.py","file_url":"https://github.com/laura-rieger/deep-explanation-penalization/blob/HEAD/src/cd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47f0c1095f604511"}},{"code_sha256_prefix":"3eb7a98b2c9df0a7","entry":"propagate_tanh_two","repo":"laura-rieger/deep-explanation-penalization","repo_kind":"official","path":"src/cd.py","file_url":"https://github.com/laura-rieger/deep-explanation-penalization/blob/HEAD/src/cd.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3eb7a98b2c9df0a7"}},{"code_sha256_prefix":"54fc0b180472e2ab","entry":"propagate_three","repo":"laura-rieger/deep-explanation-penalization","repo_kind":"official","path":"src/cd.py","file_url":"https://github.com/laura-rieger/deep-explanation-penalization/blob/HEAD/src/cd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54fc0b180472e2ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}