{"id":"https://openalex.org/W7163022189","doi":"https://doi.org/10.48550/arxiv.2605.31324","title":"Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data","display_name":"Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163022189","doi":"https://doi.org/10.48550/arxiv.2605.31324"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.31324","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31324","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.31324","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137603615","display_name":"Hee-Sung Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Hee-Sung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137565703","display_name":"Hyeonseong Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Hyeonseong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101790501","display_name":"Sungyoon Lee","orcid":"https://orcid.org/0000-0002-6097-0565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Sungyoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.43970000743865967,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.43970000743865967,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.14270000159740448,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.053599998354911804,"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/generalization","display_name":"Generalization","score":0.8425999879837036},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5188000202178955},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5103999972343445},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4902999997138977},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4812000095844269},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.4805000126361847},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4246000051498413},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3788999915122986},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.3635999858379364}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8425999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6665999889373779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.593500018119812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.555899977684021},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4902999997138977},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.4805000126361847},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3610999882221222},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.3199000060558319},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29350000619888306},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2988382989","wikidata":"https://www.wikidata.org/wiki/Q370685","display_name":"Data space","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.31324","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31324","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.31324","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31324","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Estimating":[0],"the":[1,51,81,86,97,114,151],"generalization":[2,10,41,98],"gap":[3],"and":[4,21,85,146],"developing":[5],"optimization":[6],"methods":[7,135],"that":[8,64,92,119,132],"improve":[9],"are":[11],"crucial":[12],"for":[13,17,27],"deep":[14],"learning":[15,123,148],"models,":[16],"both":[18],"theoretical":[19,74],"understanding":[20],"practical":[22],"applications.":[23],"Leveraging":[24],"unlabeled":[25,157],"data":[26],"these":[28,102],"purposes":[29],"offers":[30],"significant":[31],"advantages":[32],"in":[33,120,144],"real-world":[34],"scenarios.":[35],"This":[36],"paper":[37],"introduces":[38],"a":[39],"novel":[40],"measure,":[42],"local":[43,61,78,93,111,152],"inconsistency,":[44],"derived":[45],"from":[46,156],"an":[47],"information-geometric":[48],"perspective":[49],"on":[50,101],"parameter":[52],"space":[53],"of":[54,60,133],"neural":[55],"networks.":[56],"A":[57],"key":[58],"feature":[59],"inconsistency":[62,79,94,112,153],"is":[63,154],"it":[65],"can":[66],"be":[67],"computed":[68,155],"without":[69],"explicit":[70],"labels.":[71],"We":[72,117],"establish":[73],"underpinnings":[75],"by":[76],"connecting":[77],"to":[80,131],"Fisher":[82],"information":[83],"matrix":[84],"loss":[87],"Hessian.":[88],"Empirically,":[89],"we":[90,104],"demonstrate":[91,118],"correlates":[95],"with":[96],"gap.":[99],"Based":[100],"findings,":[103],"propose":[105],"Inconsistency-Aware":[106],"Minimization":[107],"(IAM),":[108],"which":[109],"incorporates":[110],"into":[113],"training":[115],"objective.":[116],"standard":[121],"supervised":[122],"settings,":[124],"IAM":[125,141],"enhances":[126],"generalization,":[127],"achieving":[128],"performance":[129],"comparable":[130],"existing":[134],"such":[136],"as":[137],"Sharpness-Aware":[138],"Minimization.":[139],"Furthermore,":[140],"exhibits":[142],"efficacy":[143],"semi-":[145],"self-supervised":[147],"scenarios,":[149],"where":[150],"data.":[158]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-02T00:00:00"}