{"id":"https://openalex.org/W4312376326","doi":"https://doi.org/10.1109/cvpr52688.2022.01555","title":"Bayesian Invariant Risk Minimization","display_name":"Bayesian Invariant Risk Minimization","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4312376326","doi":"https://doi.org/10.1109/cvpr52688.2022.01555"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52688.2022.01555","doi":"https://doi.org/10.1109/cvpr52688.2022.01555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.01555","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5101784720","display_name":"Lin Yong","orcid":"https://orcid.org/0000-0002-0574-3837","observed_orcids":["https://orcid.org/0000-0002-0574-3837"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yong Lin","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061778641","display_name":"Hanze Dong","orcid":"https://orcid.org/0000-0002-8846-1260","observed_orcids":["https://orcid.org/0000-0002-8846-1260"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hanze Dong","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101533496","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-7308-938X","observed_orcids":["https://orcid.org/0000-0002-7308-938X"]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378792","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-5511-2558","observed_orcids":["https://orcid.org/0000-0002-5511-2558","https://orcid.org/0000-0001-5818-4285","https://orcid.org/0000-0002-7025-6365","https://orcid.org/0000-0002-8838-4963","https://orcid.org/0000-0001-6212-4891","https://orcid.org/0000-0002-3506-0180","https://orcid.org/0000-0002-6807-0641","https://orcid.org/0000-0003-1148-4322","https://orcid.org/0000-0002-0131-0129","https://orcid.org/0000-0001-8163-3050","https://orcid.org/0000-0002-3481-6062"]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5527,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97171726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"16000","last_page":"16009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.98580002784729,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.98580002784729,"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":0.0017000000225380063,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.00139999995008111,"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/invariant-risk-minimization","display_name":"invariant risk minimization","score":0.9580000042915344},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.8259999752044678},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.9020000100135803},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.8069999814033508},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.9520000219345093},{"id":"https://openalex.org/keywords/empirical-risk-minimization","display_name":"empirical risk minimization","score":0.8799999952316284},{"id":"https://openalex.org/keywords/invariant-features","display_name":"invariant features","score":0.5989999771118164},{"id":"https://openalex.org/keywords/model-size","display_name":"model size","score":0.5239999890327454}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9300563335418701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6952754259109497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6470003128051758},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6377843618392944},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.594924807548523},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.582944393157959},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5701167583465576},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.53177410364151},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.47065678238868713},{"id":"https://openalex.org/C154507838","wikidata":"https://www.wikidata.org/wiki/Q7625053","display_name":"Structural risk minimization","level":3,"score":0.46279287338256836},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4558315575122833},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3202752470970154},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.24553948640823364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18118607997894287},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13825136423110962},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr52688.2022.01555","doi":"https://doi.org/10.1109/cvpr52688.2022.01555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.01555","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-118084","doi":null,"is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-118084","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1492711822","https://openalex.org/W1494192115","https://openalex.org/W1582436621","https://openalex.org/W1902237438","https://openalex.org/W1959608418","https://openalex.org/W2047229728","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2154637324","https://openalex.org/W2194775991","https://openalex.org/W2225156818","https://openalex.org/W2412589713","https://openalex.org/W2548077621","https://openalex.org/W2566079294","https://openalex.org/W2604763608","https://openalex.org/W2790376986","https://openalex.org/W2805481182","https://openalex.org/W2883386984","https://openalex.org/W2951398059","https://openalex.org/W2953494151","https://openalex.org/W2966692724","https://openalex.org/W2979906247","https://openalex.org/W2982079119","https://openalex.org/W2991497298","https://openalex.org/W2998348840","https://openalex.org/W3006589327","https://openalex.org/W3007592798","https://openalex.org/W3016970897","https://openalex.org/W3035398303","https://openalex.org/W3035723985","https://openalex.org/W3039431315","https://openalex.org/W3089611792","https://openalex.org/W3092928935","https://openalex.org/W3096304594","https://openalex.org/W3099180329","https://openalex.org/W3118114660","https://openalex.org/W3133121425","https://openalex.org/W3150450875","https://openalex.org/W3161905328","https://openalex.org/W3167304302","https://openalex.org/W3169317873","https://openalex.org/W3170865782","https://openalex.org/W3171849353","https://openalex.org/W3181074959","https://openalex.org/W3189058335","https://openalex.org/W3206985210","https://openalex.org/W4221144371","https://openalex.org/W4245232001","https://openalex.org/W6766092863","https://openalex.org/W6790544855","https://openalex.org/W7133198412"],"related_works":["https://openalex.org/W7005922919","https://openalex.org/W3092928935","https://openalex.org/W3118395365","https://openalex.org/W3138714519","https://openalex.org/W4382239301","https://openalex.org/W6966903002","https://openalex.org/W3096304594","https://openalex.org/W7133202527","https://openalex.org/W3128062127","https://openalex.org/W4323556828"],"abstract_inverted_index":{"Generalization":[0],"under":[1],"distributional":[2],"shift":[3],"is":[4,15,129,150],"an":[5],"open":[6],"challenge":[7],"for":[8],"machine":[9],"learning.":[10],"Invariant":[11,115],"Risk":[12,116],"Minimization":[13],"(IRM)":[14],"a":[16,146],"promising":[17],"framework":[18],"to":[19,55,59,71,130,145,154],"tackle":[20],"this":[21,110],"issue":[22],"by":[23,119],"extracting":[24],"invariant":[25],"features.":[26],"However,":[27],"despite":[28],"the":[29,49,61,100,105,124,132,138,167],"potential":[30],"and":[31],"popularity":[32],"of":[33,41,134,141],"IRM,":[34],"recent":[35],"works":[36],"have":[37],"reported":[38],"negative":[39],"results":[40,158],"it":[42],"on":[43,137,159],"deep":[44,56],"models.":[45],"We":[46],"argue":[47],"that":[48,68,87,163],"failure":[50],"can":[51],"be":[52],"primarily":[53],"attributed":[54],"models'":[57],"tendency":[58],"overfit":[60],"data.":[62,107],"Specifically,":[63],"our":[64],"theoretical":[65],"analysis":[66],"shows":[67],"IRM":[69,85,135,169],"degenerates":[70],"empirical":[72,80],"risk":[73],"minimization":[74],"(ERM)":[75],"when":[76],"overfitting":[77],"occurs.":[78],"Our":[79],"evidence":[81],"also":[82],"provides":[83],"supports:":[84],"methods":[86],"work":[88],"well":[89],"in":[90],"typical":[91],"settings":[92],"significantly":[93],"deteriorate":[94],"even":[95],"if":[96],"we":[97,112],"slightly":[98],"enlarge":[99],"model":[101],"size":[102],"or":[103],"lessen":[104],"training":[106],"To":[108],"alleviate":[109],"issue,":[111],"propose":[113],"Bayesian":[114,121],"Min-imization":[117],"(BIRM)":[118],"introducing":[120],"inference":[122],"into":[123],"IRM.":[125],"The":[126],"key":[127],"motivation":[128],"estimate":[131],"penalty":[133],"based":[136],"posterior":[139],"distribution":[140],"classifiers":[142],"(as":[143],"opposed":[144],"single":[147],"classifier),":[148],"which":[149],"much":[151],"less":[152],"prone":[153],"overfitting.":[155],"Extensive":[156],"experimental":[157],"four":[160],"datasets":[161],"demonstrate":[162],"BIRM":[164],"consistently":[165],"outperforms":[166],"existing":[168],"baselines":[170],"significantly.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":13}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-01-04T00:00:00"}