{"id":"https://openalex.org/W4409149905","doi":"https://doi.org/10.1145/3690624.3709309","title":"BTFL: A Bayesian-based Test-Time Generalization Method for Internal and External Data Distributions in Federated learning","display_name":"BTFL: A Bayesian-based Test-Time Generalization Method for Internal and External Data Distributions in Federated learning","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409149905","doi":"https://doi.org/10.1145/3690624.3709309"},"language":"en","primary_location":{"id":"doi:10.1145/3690624.3709309","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3690624.3709309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","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/A5103940513","display_name":"Yu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101497182","display_name":"Bingyan Liu","orcid":"https://orcid.org/0000-0003-2613-9863"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingyan Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103940513"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90170409,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2147","last_page":"2158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9854999780654907,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9796000123023987,"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/computer-science","display_name":"Computer science","score":0.7445714473724365},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7360851764678955},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6162030696868896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5298255085945129},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5263926982879639},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5254627466201782},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3666313886642456},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12484961748123169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445714473724365},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7360851764678955},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6162030696868896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5298255085945129},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5263926982879639},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5254627466201782},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3666313886642456},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12484961748123169},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3690624.3709309","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3690624.3709309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1975294966","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2627183927","https://openalex.org/W3035012305","https://openalex.org/W3037492894","https://openalex.org/W3156024711","https://openalex.org/W3198675127","https://openalex.org/W3208166108","https://openalex.org/W4250482878","https://openalex.org/W4312517097","https://openalex.org/W4367046890","https://openalex.org/W4385567954","https://openalex.org/W4386075560","https://openalex.org/W4396757542","https://openalex.org/W4396758529","https://openalex.org/W4401856724","https://openalex.org/W4401857163","https://openalex.org/W4402753562","https://openalex.org/W7028611299"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918","https://openalex.org/W4200527723"],"abstract_inverted_index":{"Federated":[0,31,92],"Learning":[1,32,93],"(FL)":[2],"enables":[3],"multiple":[4],"clients":[5],"to":[6,23,38,51,132],"collaboratively":[7],"develop":[8],"a":[9,81,109,129,141],"global":[10,36,136],"model":[11,37],"while":[12],"maintaining":[13],"data":[14,149],"privacy.":[15],"However,":[16],"online":[17,62],"FL":[18],"deployment":[19],"faces":[20],"challenges":[21],"due":[22],"distribution":[24],"shifts":[25],"and":[26,59,66,88,102,119,135,150,157,171],"evolving":[27],"test":[28,148],"samples.":[29],"Personalized":[30],"(PFL)":[33],"tailors":[34],"the":[35,76,122],"individual":[39],"client":[40],"distributions,":[41],"but":[42],"struggles":[43],"with":[44,154,173],"Out-Of-Distribution":[45],"(OOD)":[46],"samples":[47],"during":[48,61,125],"testing,":[49],"leading":[50],"performance":[52,167],"degradation.":[53],"In":[54],"real-world":[55],"scenarios,":[56],"balancing":[57],"personalization":[58,120],"generalization":[60,112,118],"testing":[63],"is":[64],"crucial":[65],"existing":[67],"methods":[68],"primarily":[69],"focus":[70],"on":[71],"training-phase":[72],"generalization.":[73],"To":[74],"address":[75],"test-time":[77,111],"trade-off,":[78],"we":[79],"introduce":[80],"new":[82],"scenario:":[83],"Test-time":[84],"Generalization":[85],"for":[86,114],"Internal":[87,99],"External":[89,103],"Distributions":[90],"in":[91],"(TGFL),":[94],"which":[95,116],"evaluates":[96],"adaptability":[97],"under":[98],"Distribution":[100,104],"(IND)":[101],"(EXD).":[105],"We":[106],"propose":[107],"BTFL,":[108],"Bayesian-based":[110],"method":[113],"TGFL,":[115],"balances":[117],"at":[121,184],"sample":[123,152],"level":[124],"testing.":[126],"BTFL":[127,164],"employs":[128],"two-head":[130],"architecture":[131],"store":[133],"local":[134],"knowledge,":[137],"interpolating":[138],"predictions":[139],"via":[140],"dual-Bayesian":[142],"framework":[143],"that":[144,163],"considers":[145],"both":[146],"historical":[147],"current":[151],"characteristics":[153],"theoretical":[155],"guarantee":[156],"faster":[158],"speed.":[159],"Our":[160],"experiments":[161],"demonstrate":[162],"achieves":[165],"improved":[166],"across":[168],"various":[169],"datasets":[170],"models":[172],"less":[174],"time":[175],"cost.":[176],"The":[177],"source":[178],"codes":[179],"are":[180],"made":[181],"publicly":[182],"available":[183],"https://github.com/ZhouYuCS/BTFL.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}