{"id":"https://openalex.org/W4403582422","doi":"https://doi.org/10.1145/3627673.3679846","title":"Correcting Biases of Shapley Value Attributions for Informative Machine Learning Model Explanations","display_name":"Correcting Biases of Shapley Value Attributions for Informative Machine Learning Model Explanations","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582422","doi":"https://doi.org/10.1145/3627673.3679846"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055224663","display_name":"Ningsheng Zhao","orcid":"https://orcid.org/0009-0009-5437-284X"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ningsheng Zhao","raw_affiliation_strings":["Concordia University, Montreal, Quebec, Canada"],"raw_orcid":"https://orcid.org/0009-0009-5437-284X","affiliations":[{"raw_affiliation_string":"Concordia University, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101187193","display_name":"Jia Yuan Yu","orcid":"https://orcid.org/0000-0001-5768-9249"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jia Yuan Yu","raw_affiliation_strings":["Concordia University, Montreal, Quebec, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5768-9249","affiliations":[{"raw_affiliation_string":"Concordia University, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023505538","display_name":"Trang Bui","orcid":"https://orcid.org/0000-0002-7752-2611"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Trang Bui","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7752-2611","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002295748","display_name":"Krzysztof Dzi\u0119cio\u0142owski","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Krzysztof Dzieciolowski","raw_affiliation_strings":["Concordia University and Daesys Inc., Montreal, Quebec, Canada"],"raw_orcid":"https://orcid.org/0009-0007-7553-5666","affiliations":[{"raw_affiliation_string":"Concordia University and Daesys Inc., Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19248873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3331","last_page":"3340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9781000018119812,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.6913827657699585},{"id":"https://openalex.org/keywords/shapley-value","display_name":"Shapley value","score":0.6478585004806519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6339995265007019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5604046583175659},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4886641800403595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4706059396266937},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.36370009183883667},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20973336696624756},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.1910516321659088},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14049690961837769},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.13120779395103455},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12169349193572998}],"concepts":[{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.6913827657699585},{"id":"https://openalex.org/C199022921","wikidata":"https://www.wikidata.org/wiki/Q240046","display_name":"Shapley value","level":3,"score":0.6478585004806519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6339995265007019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5604046583175659},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4886641800403595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4706059396266937},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36370009183883667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20973336696624756},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.1910516321659088},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14049690961837769},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.13120779395103455},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12169349193572998}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W2006676204","https://openalex.org/W2011438884","https://openalex.org/W2117030594","https://openalex.org/W2612690371","https://openalex.org/W2969476445","https://openalex.org/W2997591727","https://openalex.org/W2999615587","https://openalex.org/W2999905431","https://openalex.org/W3005086430","https://openalex.org/W3014290757","https://openalex.org/W3146613606","https://openalex.org/W3172177573","https://openalex.org/W3201801031","https://openalex.org/W3204324161","https://openalex.org/W4300537824","https://openalex.org/W4300862723","https://openalex.org/W4318677254","https://openalex.org/W4386152782","https://openalex.org/W4391440634","https://openalex.org/W6888945715"],"related_works":["https://openalex.org/W4249226508","https://openalex.org/W2035546108","https://openalex.org/W2380202880","https://openalex.org/W4233790924","https://openalex.org/W4256656994","https://openalex.org/W3126099358","https://openalex.org/W2376361520","https://openalex.org/W2133328864","https://openalex.org/W2169227624","https://openalex.org/W2093949997"],"abstract_inverted_index":{"Shapley":[0,160],"value":[1],"attribution":[2],"(SVA)":[3],"is":[4],"an":[5],"increasingly":[6],"popular":[7,133],"Explainable":[8],"AI":[9],"(XAI)":[10],"approach":[11],"that":[12,43,104,147],"has":[13],"been":[14],"widely":[15],"used":[16],"in":[17,94],"many":[18],"recent":[19],"applied":[20],"studies":[21],"to":[22,45,75,88,117,131],"gain":[23],"new":[24],"insights":[25],"into":[26,62],"the":[27,48,119,135,139,148,153],"underlying":[28],"information":[29],"systems.":[30],"However,":[31],"most":[32],"existing":[33],"SVA":[34,137],"methods":[35,103,115,130,150],"are":[36],"error-prone,":[37],"providing":[38],"biased":[39],"or":[40],"unreliable":[41],"explanations":[42],"fail":[44],"correctly":[46],"capture":[47],"informational":[49],"dependencies":[50],"between":[51],"features":[52],"and":[53,73,77,86,109,138,158],"model":[54],"outputs.":[55],"These":[56],"explanation":[57],"errors":[58],"can":[59],"be":[60],"decomposed":[61],"two":[63,132],"components:":[64],"1)":[65],"observation":[66],"bias":[67,80],"which":[68,81],"stems":[69,82],"from":[70,83],"data":[71],"sparsity":[72],"leads":[74,87],"over-informativeness;":[76],"2)":[78],"structural":[79],"distributional":[84,124],"assumptions":[85],"under-informativeness.":[89],"To":[90],"alleviate":[91],"these":[92],"biases,":[93],"this":[95],"paper,":[96],"we":[97],"propose":[98],"a":[99],"series":[100],"of":[101,155],"refinement":[102,129],"combine":[105],"out-of-distribution":[106],"(OOD)":[107],"detection":[108],"importance":[110],"sampling.":[111],"In":[112],"essence,":[113],"our":[114,128],"aim":[116],"rectify":[118],"distribution":[120],"drift":[121],"caused":[122],"by":[123],"assumptions.":[125],"We":[126],"apply":[127],"SVAs:":[134],"marginal":[136],"surrogate":[140],"model-based":[141],"SVA.":[142],"Our":[143],"extensive":[144],"experiments":[145],"show":[146],"proposed":[149],"significantly":[151],"enhance":[152],"informativeness":[154],"both":[156],"local":[157],"global":[159],"value-based":[161],"explanations.":[162]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}