{"id":"https://openalex.org/W4387848639","doi":"https://doi.org/10.1145/3583780.3615173","title":"A Joint Training-Calibration Framework for Test-Time Personalization with Label Shift in Federated Learning","display_name":"A Joint Training-Calibration Framework for Test-Time Personalization with Label Shift in Federated Learning","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387848639","doi":"https://doi.org/10.1145/3583780.3615173"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615173","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615173","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","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/10.1145/3583780.3615173","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101613464","display_name":"Jian Xu","orcid":"https://orcid.org/0000-0001-6201-9215"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Xu","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088293566","display_name":"Shao\u2010Lun Huang","orcid":"https://orcid.org/0000-0003-2827-4022"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao-Lun Huang","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101613464"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8718,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79406879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4370","last_page":"4374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.829551637172699},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7059738636016846},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.680432915687561},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6628209352493286},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5983114838600159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5666743516921997},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5558117628097534},{"id":"https://openalex.org/keywords/scenario-testing","display_name":"Scenario testing","score":0.5165935754776001},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4551342725753784},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4250667691230774},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.3455209732055664},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32600903511047363},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2628215253353119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829551637172699},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7059738636016846},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.680432915687561},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6628209352493286},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5983114838600159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5666743516921997},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5558117628097534},{"id":"https://openalex.org/C80519477","wikidata":"https://www.wikidata.org/wiki/Q3532236","display_name":"Scenario testing","level":3,"score":0.5165935754776001},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4551342725753784},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4250667691230774},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3455209732055664},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32600903511047363},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2628215253353119},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3615173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615173","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615173","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3583780.3615173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615173","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615173","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387848639.pdf","grobid_xml":"https://content.openalex.org/works/W4387848639.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W2141253686","https://openalex.org/W2560674852","https://openalex.org/W2616198738","https://openalex.org/W2747329762","https://openalex.org/W2912213068","https://openalex.org/W2995022099","https://openalex.org/W3021654819","https://openalex.org/W3133814152","https://openalex.org/W3196371845","https://openalex.org/W6600120041","https://openalex.org/W6600512042","https://openalex.org/W6758674664"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W2085259108","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W3101081936","https://openalex.org/W4320018443"],"abstract_inverted_index":{"The":[0],"data":[1],"heterogeneity":[2],"has":[3],"been":[4],"a":[5,19,42,47,85,114],"challenging":[6],"issue":[7,94],"in":[8,11,118,145],"federated":[9],"learning":[10],"both":[12],"training":[13,113],"and":[14,46,103],"inference":[15],"stages,":[16],"which":[17,74],"motivates":[18],"variety":[20],"of":[21,112,127,139],"approaches":[22],"to":[23,88,122],"learn":[24],"either":[25,57],"personalized":[26],"models":[27],"for":[28,34,51,142],"participating":[29],"clients":[30,69,147],"or":[31,65],"test-time":[32],"adaptations":[33],"unseen":[35,146],"clients.":[36],"One":[37],"such":[38],"approach":[39],"is":[40],"employing":[41],"shared":[43],"feature":[44],"representation":[45],"customized":[48],"classifier":[49],"head":[50,61],"each":[52],"client.":[53],"However,":[54],"previous":[55],"works":[56],"neglect":[58],"the":[59,67,91,96,110,124,137],"global":[60,116],"with":[62,90,148],"rich":[63],"knowledge":[64],"assume":[66],"new":[68],"have":[70],"enough":[71],"labeled":[72],"data,":[73],"significantly":[75],"limit":[76],"their":[77],"broader":[78],"practicality.":[79],"In":[80],"this":[81],"work,":[82],"we":[83],"propose":[84],"lightweight":[86],"framework":[87,141],"tackle":[89],"label":[92,150],"shift":[93],"during":[95],"model":[97,104,117,143],"deployment":[98],"by":[99],"test":[100],"priors":[101],"estimation":[102,129],"prediction":[105],"calibration.":[106],"We":[107],"also":[108],"demonstrate":[109,136],"importance":[111],"balanced":[115],"FL":[119],"so":[120],"as":[121],"guarantee":[123],"general":[125],"effectiveness":[126],"prior":[128],"approaches.":[130],"Evaluation":[131],"results":[132],"on":[133],"benchmark":[134],"datasets":[135],"superiority":[138],"our":[140],"adaptation":[144],"unknown":[149],"shifts.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}