{"id":"https://openalex.org/W4412877201","doi":"https://doi.org/10.1145/3711896.3736857","title":"Bias Detection via Maximum Subgroup Discrepancy","display_name":"Bias Detection via Maximum Subgroup Discrepancy","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877201","doi":"https://doi.org/10.1145/3711896.3736857"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3736857","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736857","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736857","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736857","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119175173","display_name":"Ji\u0159\u00ed N\u011bme\u010dek","orcid":"https://orcid.org/0009-0005-0585-1642"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ji\u0159\u00ed N\u011bme\u010dek","raw_affiliation_strings":["Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0009-0005-0585-1642","affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045815905","display_name":"Mark Kozdoba","orcid":"https://orcid.org/0000-0002-8451-023X"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Mark Kozdoba","raw_affiliation_strings":["Technion, Haifa, Israel"],"raw_orcid":"https://orcid.org/0000-0002-8451-023X","affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116167321","display_name":"Illia Kryvoviaz","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Illia Kryvoviaz","raw_affiliation_strings":["Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0009-0002-9834-6722","affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059337672","display_name":"Tom\u00e1\u0161 Pevn\u00fd","orcid":"https://orcid.org/0000-0002-5768-9713"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Tom\u00e1\u0161 Pevn\u00fd","raw_affiliation_strings":["Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0002-5768-9713","affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003656133","display_name":"Jakub Mare\u010dek","orcid":"https://orcid.org/0000-0003-0839-0691"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jakub Mare\u010dek","raw_affiliation_strings":["Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0003-0839-0691","affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16845552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2174","last_page":"2185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11443","display_name":"Advanced Statistical Process Monitoring","score":0.9776999950408936,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11443","display_name":"Advanced Statistical Process Monitoring","score":0.9776999950408936,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9502999782562256,"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/computer-science","display_name":"Computer science","score":0.445360392332077},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3356183171272278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.445360392332077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3356183171272278}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3736857","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736857","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736857","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3736857","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736857","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736857","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G1062818326","display_name":"Human-Compatible Artificial Intelligence with Guarantees","funder_award_id":"101070568","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1471787206","display_name":null,"funder_award_id":"SGS23/184/OHK3/3T/13","funder_id":"https://openalex.org/F4320309972","funder_display_name":"\u010cesk\u00e9 Vysok\u00e9 U\u010den\u00ed Technick\u00e9 v Praze"},{"id":"https://openalex.org/G3622461675","display_name":null,"funder_award_id":"CZ.02.1.01","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6304920596","display_name":null,"funder_award_id":"101070568","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320309972","display_name":"\u010cesk\u00e9 Vysok\u00e9 U\u010den\u00ed Technick\u00e9 v Praze","ror":"https://ror.org/03kqpb082"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334253","display_name":"Research Center for Informatics, Czech Technical University in Prague","ror":null},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877201.pdf","grobid_xml":"https://content.openalex.org/works/W4412877201.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W607505555","https://openalex.org/W640074922","https://openalex.org/W1515641485","https://openalex.org/W1965555277","https://openalex.org/W1971073366","https://openalex.org/W2017496565","https://openalex.org/W2037468546","https://openalex.org/W2042322087","https://openalex.org/W2045656688","https://openalex.org/W2127090196","https://openalex.org/W2257638929","https://openalex.org/W2555206781","https://openalex.org/W2884379315","https://openalex.org/W2952058015","https://openalex.org/W2963104135","https://openalex.org/W2973214398","https://openalex.org/W2990138404","https://openalex.org/W3013899790","https://openalex.org/W3032340379","https://openalex.org/W3107422154","https://openalex.org/W3192733319","https://openalex.org/W3211519965","https://openalex.org/W4221045317","https://openalex.org/W4247500441","https://openalex.org/W4281931618","https://openalex.org/W4287245321","https://openalex.org/W4315705132","https://openalex.org/W4385764410","https://openalex.org/W4385768144","https://openalex.org/W4390187812","https://openalex.org/W4391420782","https://openalex.org/W4391547503","https://openalex.org/W4394769107","https://openalex.org/W4406755120","https://openalex.org/W4413832492","https://openalex.org/W6795007937","https://openalex.org/W6799867637"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027"],"abstract_inverted_index":{"Bias":[0],"evaluation":[1],"is":[2,121,155],"fundamental":[3],"to":[4,42,61,70,162],"trustworthy":[5],"AI,":[6],"both":[7],"in":[8,15,75,123],"terms":[9,16],"of":[10,17,21,34,86,110,126,206,214,221],"checking":[11,18],"data":[12,25],"quality":[13],"and":[14,55,182,200,218],"the":[19,32,52,56,88,108,118,124,142,152,164,203],"outputs":[20],"AI":[22],"systems.In":[23],"testing":[24],"quality,":[26],"for":[27,104,132,140],"example,":[28],"one":[29],"may":[30,68,112],"study":[31],"distance":[33,143,154],"a":[35,40,43,72,83,137,173],"given":[36,44],"dataset,":[37],"viewed":[38],"as":[39,51],"distribution,":[41],"ground-truth":[45],"reference":[46],"dataset.However,":[47],"classical":[48],"metrics,":[49],"such":[50],"Total":[53],"Variation":[54],"Wasserstein":[57],"distances,":[58,181],"are":[59,97,102],"known":[60],"have":[62,168],"high":[63],"sample":[64,119],"complexities":[65],"and,":[66],"therefore,":[67],"fail":[69],"provide":[71,136],"meaningful":[73],"distinction":[74],"many":[76],"practical":[77,133,138],"scenarios.In":[78],"this":[79,93,189],"paper,":[80],"we":[81,115,135,171],"propose":[82],"new":[84],"notion":[85],"distance,":[87],"Maximum":[89],"Subgroup":[90],"Discrepancy":[91],"(MSD).In":[92],"metric,":[94],"two":[95],"distributions":[96],"close":[98],"if,":[99],"roughly,":[100],"discrepancies":[101],"low":[103],"all":[105],"feature":[106],"subgroups.While":[107],"number":[109,125],"subgroups":[111],"be":[113],"exponential,":[114],"show":[116,183],"that":[117,151,184],"complexity":[120],"linear":[122],"features,":[127],"thus":[128,158],"making":[129],"it":[130,196],"feasible":[131],"applications.Moreover,":[134],"algorithm":[139],"evaluating":[141],"based":[144],"on":[145,208],"Mixedinteger":[146],"optimization":[147],"(MIO).We":[148],"also":[149],"note":[150],"proposed":[153],"easily":[156],"interpretable,":[157],"providing":[159],"clearer":[160],"paths":[161],"fixing":[163],"biases":[165],"once":[166],"they":[167],"been":[169],"identified.Finally,":[170],"describe":[172],"natural":[174],"general":[175],"bias":[176],"detection":[177],"framework,":[178],"termed":[179],"MSDD":[180],"MSD":[185,193,207],"aligns":[186],"well":[187],"with":[188,197],"framework.We":[190],"empirically":[191],"evaluate":[192],"by":[194,201],"comparing":[195],"other":[198],"metrics":[199],"demonstrating":[202],"above":[204],"properties":[205],"real-world":[209],"datasets.":[210],"CCS":[211],"Concepts":[212],"Theory":[213],"computation":[215],"Complexity":[216],"theory":[217],"logic;":[219],"Mathematics":[220],"computing":[222],"Multivariate":[223],"statistics.":[224]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}