{"id":"https://openalex.org/W4414360272","doi":"https://doi.org/10.24963/ijcai.2025/677","title":"Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization","display_name":"Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360272","doi":"https://doi.org/10.24963/ijcai.2025/677"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/677","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","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/A5079754643","display_name":"Zhuang Qi","orcid":"https://orcid.org/0000-0003-3433-7413"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhuang Qi","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035134024","display_name":"Sijin Zhou","orcid":"https://orcid.org/0000-0003-2044-1738"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sijin Zhou","raw_affiliation_strings":["Monash Unversity"],"affiliations":[{"raw_affiliation_string":"Monash Unversity","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100629169","display_name":"Lei Meng","orcid":"https://orcid.org/0000-0002-0273-5946"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Meng","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020194895","display_name":"Han Hu","orcid":"https://orcid.org/0000-0001-7532-0496"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Hu","raw_affiliation_strings":["Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064069283","display_name":"Han Yu","orcid":"https://orcid.org/0000-0001-6893-8650"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Han Yu","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101536417","display_name":"Xiangxu Meng","orcid":"https://orcid.org/0000-0001-7290-5659"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxu Meng","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5079754643"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13989794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6084","last_page":"6092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9850999712944031,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9850999712944031,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9006999731063843,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/debiasing","display_name":"Debiasing","score":0.906000018119812},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6172999739646912},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.4936000108718872},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46219998598098755},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3935999870300293},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.3781000077724457},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.3571000099182129},{"id":"https://openalex.org/keywords/unobservable","display_name":"Unobservable","score":0.3531999886035919},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.35260000824928284}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.906000018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533000111579895},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6051999926567078},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5705000162124634},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C95203288","wikidata":"https://www.wikidata.org/wiki/Q221682","display_name":"Semaphore","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/677","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Attribute":[0],"bias":[1],"in":[2,158,192],"federated":[3],"learning":[4,16,37,103,145],"(FL)":[5],"typically":[6],"leads":[7],"local":[8],"models":[9],"to":[10,14,40,83,93,109,135,147,151,187,196],"optimize":[11],"inconsistently":[12],"due":[13],"the":[15,51,55,69,85,122,129,133,137,153,156,164,184],"of":[17,50,155],"non-causal":[18],"associations,":[19],"resulting":[20],"degraded":[21],"performance.":[22,62],"Existing":[23],"methods":[24],"either":[25],"use":[26],"data":[27],"augmentation":[28],"for":[29,36,105],"increasing":[30],"sample":[31],"diversity":[32],"or":[33],"knowledge":[34],"distillation":[35],"invariant":[38],"representations":[39,168],"address":[41,64],"this":[42],"problem.":[43],"However,":[44],"they":[45],"lack":[46],"a":[47,79,119],"comprehensive":[48],"analysis":[49],"inference":[52,87],"paths,":[53],"and":[54,72,89,112,124],"interference":[56],"from":[57,131],"confounding":[58,95],"factors":[59],"limits":[60],"their":[61],"To":[63],"these":[65],"limitations,":[66],"we":[67,98,140],"propose":[68],"Federated":[70],"Deconfounding":[71],"Debiasing":[73],"Learning":[74],"(FedDDL)":[75],"method.":[76],"It":[77],"constructs":[78],"structured":[80],"causal":[81,149,170],"graph":[82],"analyze":[84],"model":[86,130,185],"process,":[88],"performs":[90],"backdoor":[91],"adjustment":[92],"eliminate":[94],"paths.":[96],"Specifically,":[97],"design":[99,141],"an":[100,142],"intra-client":[101],"deconfounding":[102],"module":[104,146],"computer":[106],"vision":[107],"tasks":[108],"decouple":[110],"background":[111,123,134,157],"objects,":[113],"generating":[114],"counterfactual":[115],"samples":[116],"that":[117,180],"establish":[118],"connection":[120],"between":[121,166],"any":[125],"label,":[126],"which":[127],"stops":[128],"using":[132],"infer":[136],"label.":[138],"Moreover,":[139],"inter-client":[143],"debiasing":[144],"construct":[148],"prototypes":[150],"reduce":[152],"proportion":[154],"prototype":[159],"components.":[160],"Notably,":[161],"it":[162],"bridges":[163],"gap":[165],"heterogeneous":[167],"via":[169],"prototypical":[171],"regularization.":[172],"Extensive":[173],"experiments":[174],"on":[175,189,201],"2":[176],"benchmarking":[177],"datasets":[178],"demonstrate":[179],"FedDDL":[181],"significantly":[182],"enhances":[183],"capability":[186],"focus":[188],"main":[190],"objects":[191],"unseen":[193],"data,":[194],"leading":[195],"4.5%":[197],"higher":[198],"Top-1":[199],"Accuracy":[200],"average":[202],"over":[203],"9":[204],"state-of-the-art":[205],"existing":[206],"methods.":[207]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}