{"id":"https://openalex.org/W4406459256","doi":"https://doi.org/10.1109/bigdata62323.2024.10825347","title":"Tackling Data Heterogeneity in Federated Learning through Global Density Estimation","display_name":"Tackling Data Heterogeneity in Federated Learning through Global Density Estimation","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406459256","doi":"https://doi.org/10.1109/bigdata62323.2024.10825347"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5025288512","display_name":"Sagnik Ghosh","orcid":"https://orcid.org/0000-0002-5126-5362"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sagnik Ghosh","raw_affiliation_strings":["Indian Institute of Technology Mandi,Vision Intelligence and Machine Learning (VIML) Group School of Computing and Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Mandi,Vision Intelligence and Machine Learning (VIML) Group School of Computing and Electrical Engineering","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086073362","display_name":"Alok Kumar Singh Kushwaha","orcid":"https://orcid.org/0000-0003-2928-998X"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Avinash Kushwaha","raw_affiliation_strings":["Indian Institute of Technology Mandi,Vision Intelligence and Machine Learning (VIML) Group School of Computing and Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Mandi,Vision Intelligence and Machine Learning (VIML) Group School of Computing and Electrical Engineering","institution_ids":["https://openalex.org/I9579091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077717460","display_name":"Dinesh Singh","orcid":"https://orcid.org/0000-0001-8889-9847"},"institutions":[{"id":"https://openalex.org/I9579091","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34","country_code":"IN","type":"education","lineage":["https://openalex.org/I9579091"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dinesh Singh","raw_affiliation_strings":["Indian Institute of Technology Mandi,Vision Intelligence and Machine Learning (VIML) Group School of Computing and Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Mandi,Vision Intelligence and Machine Learning (VIML) Group School of Computing and Electrical Engineering","institution_ids":["https://openalex.org/I9579091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025288512"],"corresponding_institution_ids":["https://openalex.org/I9579091"],"apc_list":null,"apc_paid":null,"fwci":0.7283,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78513787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7764","last_page":"7773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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":0.9983000159263611,"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":0.9919000267982483,"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":0.6518320441246033},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5546433925628662},{"id":"https://openalex.org/keywords/density-estimation","display_name":"Density estimation","score":0.49735310673713684},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39197176694869995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35772156715393066},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3291638493537903},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2047019898891449},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.088072270154953},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08354121446609497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6518320441246033},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5546433925628662},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.49735310673713684},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39197176694869995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35772156715393066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3291638493537903},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2047019898891449},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.088072270154953},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08354121446609497},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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":41,"referenced_works":["https://openalex.org/W2007339694","https://openalex.org/W2535838896","https://openalex.org/W2563424502","https://openalex.org/W2734775742","https://openalex.org/W2963819344","https://openalex.org/W3034748927","https://openalex.org/W3043723611","https://openalex.org/W3086809868","https://openalex.org/W3118608800","https://openalex.org/W3125494587","https://openalex.org/W3156841666","https://openalex.org/W3178336997","https://openalex.org/W3182158470","https://openalex.org/W3194195161","https://openalex.org/W3197072507","https://openalex.org/W3204874618","https://openalex.org/W4225309593","https://openalex.org/W4289147229","https://openalex.org/W4297687186","https://openalex.org/W4299283926","https://openalex.org/W4300672471","https://openalex.org/W4312869277","https://openalex.org/W4312950667","https://openalex.org/W4386076561","https://openalex.org/W4387449166","https://openalex.org/W6728757088","https://openalex.org/W6741131401","https://openalex.org/W6756756286","https://openalex.org/W6759238902","https://openalex.org/W6763048141","https://openalex.org/W6773817997","https://openalex.org/W6773976177","https://openalex.org/W6776372214","https://openalex.org/W6779525423","https://openalex.org/W6781318954","https://openalex.org/W6786597537","https://openalex.org/W6787972765","https://openalex.org/W6798417033","https://openalex.org/W6800755839","https://openalex.org/W6838907135","https://openalex.org/W6839109453"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Federated":[0],"learning":[1],"is":[2,18,110],"gaining":[3],"popularity":[4],"for":[5,47,54,129,196],"its":[6],"largely":[7],"accepted":[8],"paradigm":[9],"of":[10,29,36,68,104,118,126],"privacy":[11,88],"protection.":[12],"However,":[13],"data":[14,37,87,95,119,147],"heterogeneity":[15,93,117,148],"among":[16,120,149],"clients":[17,39,70,121],"often":[19],"the":[20,27,41,65,73,91,99,105,115,124,137,181,190],"primary":[21],"challenge":[22],"in":[23,94,153,184],"federated":[24,102],"learning,":[25],"hindering":[26],"convergence":[28],"deep":[30],"neural":[31],"networks.":[32],"The":[33,194],"non-IID":[34],"nature":[35],"across":[38,97],"escalates":[40],"computational":[42],"cost":[43],"and":[44,52,157,175],"communication":[45,186,192],"overhead":[46],"models":[48,128,133,169],"trained":[49,165],"locally":[50],"on-device":[51,142],"shared":[53],"global":[55,74],"averaging.":[56],"To":[57],"mitigate":[58,114],"this":[59],"issue,":[60],"we":[61],"try":[62],"to":[63,113,145],"preserve":[64],"statistical":[66,92],"parameters":[67],"local":[69],"by":[71],"estimating":[72],"density":[75],"using":[76,140,166],"Gaussian":[77],"mixture":[78],"model.":[79],"Our":[80,177],"study":[81],"primarily":[82],"focuses":[83],"on":[84],"preserving":[85],"client":[86,138],"while":[89],"addressing":[90],"distribution":[96],"all":[98],"clients.":[100,150],"A":[101],"implementation":[103,198],"distribution-preserving":[106],"sampling":[107],"algorithm,":[108],"FedDpS":[109],"put":[111],"forward":[112],"high":[116],"thereby":[122,188],"facilitating":[123],"training":[125],"DNN":[127],"faster":[130],"convergence.":[131],"Local":[132],"are":[134],"built":[135],"at":[136,202],"level":[139],"our":[141,197],"algorithm":[143],"designed":[144],"tackle":[146],"Significant":[151],"improvements":[152],"test":[154],"accuracy,":[155],"F1-score,":[156],"other":[158],"evaluation":[159],"metrics":[160],"have":[161],"been":[162],"observed":[163],"when":[164],"state-of-the-art":[167],"optimization":[168],"like":[170],"FedAvg,":[171],"FedProx,":[172],"FedAdam,":[173],"FedAwS,":[174],"MOON.":[176],"proposed":[178],"method":[179],"achieves":[180],"target":[182],"performance":[183],"fewer":[185],"rounds":[187],"reducing":[189],"overall":[191],"cost.":[193],"code":[195],"can":[199],"be":[200],"found":[201],"https://github.com/sagnik04g/FedDpS.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}