{"id":"https://openalex.org/W7203485836","doi":"https://doi.org/10.48550/arxiv.2608.13190","title":"ProME: Prototype-Margin Environments with Repair-Aware Selection for Group-Robust Learning","display_name":"ProME: Prototype-Margin Environments with Repair-Aware Selection for Group-Robust Learning","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W7203485836","doi":"https://doi.org/10.48550/arxiv.2608.13190"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.13190","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13190","pdf_url":"https://arxiv.org/pdf/2608.13190","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.13190","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125761244","display_name":"Qianqian Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Qianqian","raw_affiliation_strings":["Department of Statistics and Data Science , Southern University of Science and Technology , Shenzhen , China","Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science , Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet , Shenzhen , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129721170","display_name":"Yunshan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yunshan","raw_affiliation_strings":["Department of Statistics and Data Science , Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science , Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147191912","display_name":"Dawei Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Dawei","raw_affiliation_strings":["Department of Statistics and Data Science , Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science , Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027015100","display_name":"Wenwu Gong","orcid":"https://orcid.org/0000-0002-8019-0582","observed_orcids":["https://orcid.org/0000-0002-8019-0582"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong, Wenwu","raw_affiliation_strings":["Department of Statistics and Data Science , Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science , Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5144426484","display_name":"Lili Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Lili","raw_affiliation_strings":["Department of Statistics and Data Science , Southern University of Science and Technology , Shenzhen , China","Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science , Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet , Shenzhen , China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.48489999771118164,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.48489999771118164,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.08370000123977661,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.06769999861717224,"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/shortcut-learning","display_name":"shortcut learning","score":0.5899999737739563},{"id":"https://openalex.org/keywords/representation-selection","display_name":"representation selection","score":0.42100000381469727},{"id":"https://openalex.org/keywords/promes","display_name":"ProMES","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254999876022339},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7038000226020813},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6759999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6304000020027161},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.605400025844574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5375000238418579},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3328999876976013},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.13190","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13190","pdf_url":"https://arxiv.org/pdf/2608.13190","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.13190","doi":"https://doi.org/10.48550/arxiv.2608.13190","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.13190","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.13190","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13190","pdf_url":"https://arxiv.org/pdf/2608.13190","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4418773921","display_name":null,"funder_award_id":"ZDSYS20210623092007023","funder_id":"https://openalex.org/F4320327605","funder_display_name":"Southern University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320327605","display_name":"Southern University of Science and Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203485836.pdf","grobid_xml":"https://content.openalex.org/works/W7203485836.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4221165976","https://openalex.org/W4226507084","https://openalex.org/W4293566550","https://openalex.org/W7117460018","https://openalex.org/W4300973223","https://openalex.org/W7128358842","https://openalex.org/W3166510965","https://openalex.org/W7133227708","https://openalex.org/W3201768173","https://openalex.org/W4403346150"],"abstract_inverted_index":{"Group-robust":[0],"learning":[1],"is":[2],"crucial":[3],"for":[4,121],"maintaining":[5],"accuracy":[6,162],"on":[7,98],"rare":[8],"subpopulations":[9],"when":[10],"training-group":[11,52],"labels":[12,53],"are":[13],"unavailable.":[14],"However,":[15],"existing":[16],"methods":[17,166],"often":[18],"infer":[19],"environments":[20,57,87,120],"from":[21],"a":[22,94,122],"separate":[23],"reference":[24],"model":[25],"and":[26,63,92,125,155],"select":[27],"representations":[28],"before":[29],"fitting":[30],"the":[31,41,55,73,89,104,114,118,133,158,164,168],"classifier":[32,150],"used":[33],"at":[34,80],"deployment,":[35],"leaving":[36],"both":[37,70],"decisions":[38,71],"misaligned":[39],"with":[40,58,72,167],"deployed":[42,74],"predictor.":[43,75],"In":[44],"this":[45,129],"work,":[46],"we":[47],"formulate":[48],"group":[49],"robustness":[50],"without":[51],"as":[54],"endogenous":[56],"repair-aware":[59],"selection":[60],"(ERAS)":[61],"problem,":[62],"propose":[64],"ProME":[65,76,156],"(Prototype-Margin":[66],"Environments)":[67],"to":[68,83,102,132],"align":[69],"splits":[77],"prototype":[78,145],"margins":[79,146],"their":[81],"median":[82],"construct":[84],"approximately":[85],"balanced":[86],"along":[88],"training":[90],"trajectory,":[91],"fits":[93],"group-balanced":[95],"linear":[96],"head":[97],"group-annotated":[99],"validation":[100,108],"data":[101],"rank":[103],"resulting":[105],"predictors":[106],"by":[107],"worst-group":[109,161],"accuracy.":[110],"We":[111],"theoretically":[112],"bound":[113,130],"worst":[115],"risk":[116],"across":[117],"inferred":[119],"fixed":[123],"predictor":[124],"partition,":[126],"showing":[127],"that":[128,144],"transfers":[131],"oracle":[134],"groups":[135],"under":[136],"an":[137],"explicit":[138],"alignment":[139],"condition.":[140],"Extensive":[141],"experiments":[142],"show":[143],"enrich":[147],"shortcut-conflicting":[148],"examples,":[149],"repair":[151],"reshapes":[152],"candidate":[153],"evaluation,":[154],"achieves":[157],"highest":[159],"average":[160],"among":[163],"compared":[165],"same":[169],"group-label":[170],"access.":[171]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-15T00:00:00"}