{"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/learning-baseline-values-for-shapley-values","title":"Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?","arxiv_id":"2105.10719","date":"2021-05-22","proceeding":null,"authors":["Jie Ren","Zhanpeng Zhou","Qirui Chen","Quanshi Zhang"],"abstract":"Masking some input variables of a deep neural network (DNN) and computing output changes on the masked input sample represent a typical way to compute attributions of input variables in the sample. People usually mask an input variable using its baseline value. However, there is no theory to examine whether baseline value faithfully represents the absence of an input variable, \\emph{i.e.,} removing all signals from the input variable. Fortunately, recent studies show that the inference score of a DNN can be strictly disentangled into a set of causal patterns (or concepts) encoded by the DNN. Therefore, we propose to use causal patterns to examine the faithfulness of baseline values. More crucially, it is proven that causal patterns can be explained as the elementary rationale of the Shapley value. Furthermore, we propose a method to learn optimal baseline values, and experimental results have demonstrated its effectiveness.","url_abs":"https://arxiv.org/abs/2105.10719v4","url_pdf":"https://arxiv.org/pdf/2105.10719v4.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":"learning-baseline-values-for-shapley-values","repo_url":"https://github.com/zzp1012/faithful-baseline-value","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2105.10719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.10719"}},"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":"deterministic:regex_extraction","url":"https://github.com/zzp1012/faithful-baseline-value","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"402b35d98c0339c9","entry":"calculate_grad","repo":"zzp1012/faithful-baseline-value","repo_kind":"official","path":"src/baseline/tabular.py","file_url":"https://github.com/zzp1012/faithful-baseline-value/blob/HEAD/src/baseline/tabular.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":"402b35d98c0339c9"}},{"code_sha256_prefix":"165895fb91ad2396","entry":"compute_vS","repo":"zzp1012/faithful-baseline-value","repo_kind":"official","path":"src/baseline/tabular.py","file_url":"https://github.com/zzp1012/faithful-baseline-value/blob/HEAD/src/baseline/tabular.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":"165895fb91ad2396"}},{"code_sha256_prefix":"09edb8b08dd5a895","entry":"learn_baseline","repo":"zzp1012/faithful-baseline-value","repo_kind":"official","path":"src/baseline/tabular.py","file_url":"https://github.com/zzp1012/faithful-baseline-value/blob/HEAD/src/baseline/tabular.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":"09edb8b08dd5a895"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}