{"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/explanations-of-black-box-models-based-on-1","title":"Explanations of Black-Box Models based on Directional Feature Interactions","arxiv_id":"2304.07670","date":"2023-04-16","proceeding":"ICLR 2022 4","authors":["Aria Masoomi","Davin Hill","Zhonghui Xu","Craig P Hersh","Edwin K. Silverman","Peter J. Castaldi","Stratis Ioannidis","Jennifer Dy"],"abstract":"As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent. Several recent works explain black-box models by capturing the most influential features for prediction per instance; such explanation methods are univariate, as they characterize importance per feature. We extend univariate explanation to a higher-order; this enhances explainability, as bivariate methods can capture feature interactions in black-box models, represented as a directed graph. Analyzing this graph enables us to discover groups of features that are equally important (i.e., interchangeable), while the notion of directionality allows us to identify the most influential features. We apply our bivariate method on Shapley value explanations, and experimentally demonstrate the ability of directional explanations to discover feature interactions. We show the superiority of our method against state-of-the-art on CIFAR10, IMDB, Census, Divorce, Drug, and gene data.","url_abs":"https://arxiv.org/abs/2304.07670v1","url_pdf":"https://arxiv.org/pdf/2304.07670v1.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":"explanations-of-black-box-models-based-on-1","repo_url":"https://github.com/davinhill/BivariateShapley","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.07670","atlas_url":"https://app.syntology.ai/?focus=2304.07670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.07670"}},"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/davinhill/BivariateShapley","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"96e451fa9df5d161","entry":"calc_train_accy","repo":"davinhill/BivariateShapley","repo_kind":"official","path":"BlackBox_Models/CIFAR10/CIFAR10_baseline.py","file_url":"https://github.com/davinhill/BivariateShapley/blob/HEAD/BlackBox_Models/CIFAR10/CIFAR10_baseline.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":"96e451fa9df5d161"}},{"code_sha256_prefix":"7440d21dad446d7f","entry":"list2cuda","repo":"davinhill/BivariateShapley","repo_kind":"official","path":"BivariateShapley/utils_shapley.py","file_url":"https://github.com/davinhill/BivariateShapley/blob/HEAD/BivariateShapley/utils_shapley.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":"7440d21dad446d7f"}},{"code_sha256_prefix":"c1763033a3cd227a","entry":"load_data","repo":"davinhill/BivariateShapley","repo_kind":"official","path":"BlackBox_Models/IMDB/load_data.py","file_url":"https://github.com/davinhill/BivariateShapley/blob/HEAD/BlackBox_Models/IMDB/load_data.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":"c1763033a3cd227a"}},{"code_sha256_prefix":"777635b869239c8c","entry":"numpy2cuda","repo":"davinhill/BivariateShapley","repo_kind":"official","path":"BivariateShapley/utils_shapley.py","file_url":"https://github.com/davinhill/BivariateShapley/blob/HEAD/BivariateShapley/utils_shapley.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":"777635b869239c8c"}},{"code_sha256_prefix":"5bc70e784a3ff6ae","entry":"pad_collate","repo":"davinhill/BivariateShapley","repo_kind":"official","path":"BlackBox_Models/IMDB/load_data.py","file_url":"https://github.com/davinhill/BivariateShapley/blob/HEAD/BlackBox_Models/IMDB/load_data.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":"5bc70e784a3ff6ae"}},{"code_sha256_prefix":"3df0ea6c0269c048","entry":"tensor2numpy","repo":"davinhill/BivariateShapley","repo_kind":"official","path":"BivariateShapley/utils_shapley.py","file_url":"https://github.com/davinhill/BivariateShapley/blob/HEAD/BivariateShapley/utils_shapley.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":"3df0ea6c0269c048"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}