{"id":"https://openalex.org/W4416249768","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227886","title":"Gradient-Aware Participation for Energy Reduction in Federated Learning with Extreme Label Skew","display_name":"Gradient-Aware Participation for Energy Reduction in Federated Learning with Extreme Label Skew","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249768","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227886"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5011685545","display_name":"Erich Malan","orcid":"https://orcid.org/0000-0003-1887-9060"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Erich Malan","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering,Turin,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084909548","display_name":"Valentino Peluso","orcid":"https://orcid.org/0000-0003-0527-8602"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Valentino Peluso","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering,Turin,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034581393","display_name":"Andrea Calimera","orcid":"https://orcid.org/0000-0001-5881-3811"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Calimera","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering,Turin,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108136013","display_name":"Enrico Macii","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enrico Macii","raw_affiliation_strings":["Politecnico di Torino,Interuniversity Department of Regional and Urban Studies and Planning,Turin,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Interuniversity Department of Regional and Urban Studies and Planning,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011685545"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19390005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.439300000667572,"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":0.439300000667572,"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":0.24549999833106995,"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":0.06930000334978104,"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/energy-consumption","display_name":"Energy consumption","score":0.7276999950408936},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.7271999716758728},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6687999963760376},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.6036999821662903},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5113000273704529},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.49050000309944153},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4422000050544739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7574999928474426},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.7276999950408936},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.7271999716758728},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6687999963760376},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4122999906539917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3806000053882599},{"id":"https://openalex.org/C30772137","wikidata":"https://www.wikidata.org/wiki/Q5164762","display_name":"Consumption (sociology)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34220001101493835},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3019999861717224},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.2637999951839447}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":20,"referenced_works":["https://openalex.org/W3108946571","https://openalex.org/W3168213397","https://openalex.org/W3182125009","https://openalex.org/W3200881607","https://openalex.org/W4285506349","https://openalex.org/W4319069175","https://openalex.org/W4381850046","https://openalex.org/W4385338532","https://openalex.org/W4386264851","https://openalex.org/W4387968262","https://openalex.org/W4390693441","https://openalex.org/W4392910504","https://openalex.org/W4393159708","https://openalex.org/W4396734345","https://openalex.org/W4400879910","https://openalex.org/W4401853290","https://openalex.org/W4403577461","https://openalex.org/W4406014515","https://openalex.org/W4406894392","https://openalex.org/W4409364536"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"enables":[3],"distributed":[4],"clients":[5,59,119],"to":[6,76,146,169,175],"train":[7],"a":[8,39,45,54,91],"global":[9,129],"classification":[10],"model":[11,56,101],"collaboratively":[12],"while":[13,99],"preserving":[14,100],"data":[15,65],"privacy.":[16],"A":[17],"major":[18],"challenge":[19],"in":[20,68],"FL":[21,86],"is":[22],"ensuring":[23],"efficient":[24],"training":[25,81,121],"with":[26,87,104],"limited":[27],"computing":[28],"and":[29,71,150,162],"communication":[30],"resources,":[31],"especially":[32],"when":[33],"clients\u2019":[34],"datasets":[35],"contain":[36],"samples":[37],"from":[38,58],"restricted":[40],"subset":[41],"of":[42,117,127,157],"target":[43],"classes,":[44],"problem":[46],"known":[47],"as":[48],"extreme":[49,105],"label":[50,106],"skew.":[51,107],"Under":[52],"such":[53],"condition,":[55],"updates":[57],"are":[60],"biased":[61],"toward":[62,138],"their":[63],"local":[64],"distributions,":[66],"resulting":[67],"slow":[69],"convergence":[70,139],"increased":[72],"energy":[73,97,172],"consumption":[74,98],"due":[75],"the":[77,111,115,125,128,143,155],"need":[78],"for":[79],"additional":[80],"rounds.":[82],"This":[83],"paper":[84],"introduces":[85],"Gradient-Aware":[88],"Participation":[89],"(FedGAP),":[90],"novel":[92],"strategy":[93],"aimed":[94],"at":[95],"reducing":[96],"accuracy":[102],"even":[103],"FedGAP":[108,141,166],"dynamically":[109],"adjusts":[110],"cohort":[112,144],"size,":[113],"i.e.,":[114],"number":[116],"participating":[118],"per":[120],"round,":[122],"based":[123],"on":[124,160],"evolution":[126],"model\u2019s":[130],"pseudo-gradient.":[131],"By":[132],"detecting":[133],"stagnant":[134],"phases":[135],"where":[136],"progress":[137],"stalls,":[140],"increases":[142],"size":[145],"escape":[147],"suboptimal":[148],"regions":[149],"accelerate":[151],"learning,":[152],"thereby":[153],"minimizing":[154],"waste":[156],"resources.":[158],"Experiments":[159],"CIFAR-10":[161],"CIFAR-100":[163],"demonstrate":[164],"that":[165],"achieves":[167],"up":[168],"2.74\u00d7":[170],"greater":[171],"efficiency":[173],"compared":[174],"state-of-the-art":[176],"methods":[177],"without":[178],"compromising":[179],"accuracy.":[180]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}