{"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/understanding-global-feature-contributions","title":"Understanding Global Feature Contributions With Additive Importance Measures","arxiv_id":"2004.00668","date":"2020-04-01","proceeding":"NeurIPS 2020 12","authors":["Ian Covert","Scott Lundberg","Su-In Lee"],"abstract":"Understanding the inner workings of complex machine learning models is a long-standing problem and most recent research has focused on local interpretability. To assess the role of individual input features in a global sense, we explore the perspective of defining feature importance through the predictive power associated with each feature. We introduce two notions of predictive power (model-based and universal) and formalize this approach with a framework of additive importance measures, which unifies numerous methods in the literature. We then propose SAGE, a model-agnostic method that quantifies predictive power while accounting for feature interactions. Our experiments show that SAGE can be calculated efficiently and that it assigns more accurate importance values than other methods.","url_abs":"https://arxiv.org/abs/2004.00668v2","url_pdf":"https://arxiv.org/pdf/2004.00668v2.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":"understanding-global-feature-contributions","repo_url":"https://github.com/iancovert/sage","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"understanding-global-feature-contributions","repo_url":"https://github.com/galdeia/iirsbenchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"understanding-global-feature-contributions","repo_url":"https://github.com/iancovert/shapley-regression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"understanding-global-feature-contributions","repo_url":"https://github.com/nliulab/sim-shapley","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.00668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.00668"}},"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/iancovert/sage","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iancovert/shapley-regression","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/galdeia/iirsbenchmark","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nliulab/sim-shapley","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"listed":{"samples":4,"ran":2,"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":4,"samples":[{"code_sha256_prefix":"6addeecb4c273c67","entry":"calculate_A","repo":"nliulab/sim-shapley","repo_kind":"listed","path":"sage/kernel_estimator.py","file_url":"https://github.com/nliulab/sim-shapley/blob/HEAD/sage/kernel_estimator.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6addeecb4c273c67"}},{"code_sha256_prefix":"0ad549d6b95dcb4c","entry":"calculate_result","repo":"nliulab/sim-shapley","repo_kind":"listed","path":"sage/kernel_estimator.py","file_url":"https://github.com/nliulab/sim-shapley/blob/HEAD/sage/kernel_estimator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ad549d6b95dcb4c"}},{"code_sha256_prefix":"c36bfcaf45ed55ed","entry":"KernelEstimator","repo":"nliulab/sim-shapley","repo_kind":"listed","path":"sage/kernel_estimator.py","file_url":"https://github.com/nliulab/sim-shapley/blob/HEAD/sage/kernel_estimator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c36bfcaf45ed55ed"}},{"code_sha256_prefix":"65b4135afabeaeae","entry":"estimate_constraints","repo":"nliulab/sim-shapley","repo_kind":"listed","path":"sage/kernel_estimator.py","file_url":"https://github.com/nliulab/sim-shapley/blob/HEAD/sage/kernel_estimator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"65b4135afabeaeae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}