{"id":"https://openalex.org/W7162142154","doi":"https://doi.org/10.1109/percom67906.2026.11524552","title":"Fed-CASQ: Enhancing Class-Wise Accuracy in Pervasive Federated Learning with Class-Aware Scaling and Quantization","display_name":"Fed-CASQ: Enhancing Class-Wise Accuracy in Pervasive Federated Learning with Class-Aware Scaling and Quantization","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7162142154","doi":"https://doi.org/10.1109/percom67906.2026.11524552"},"language":null,"primary_location":{"id":"doi:10.1109/percom67906.2026.11524552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/percom67906.2026.11524552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Pervasive Computing and Communications (PerCom)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102926029","display_name":"Emon Dey","orcid":"https://orcid.org/0000-0002-1290-0378"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emon Dey","raw_affiliation_strings":["University of Maryland,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109114460","display_name":"Anuradha Ravi","orcid":"https://orcid.org/0000-0002-1678-1863"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anuradha Ravi","raw_affiliation_strings":["University of Maryland,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078879236","display_name":"Gaurav Shinde","orcid":"https://orcid.org/0009-0004-5961-9526"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Shinde","raw_affiliation_strings":["University of Maryland,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066226035","display_name":"Garvit Chugh","orcid":"https://orcid.org/0000-0002-0354-9731"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Garvit Chugh","raw_affiliation_strings":["Indian Institute of Technology,Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026627445","display_name":"Indrajeet Ghosh","orcid":"https://orcid.org/0000-0003-2868-3766"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Indrajeet Ghosh","raw_affiliation_strings":["University of Virginia,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia,USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054849647","display_name":"Archan Misra","orcid":"https://orcid.org/0000-0003-1212-1769"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Archan Misra","raw_affiliation_strings":["Singapore Management University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University,Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068320631","display_name":"Nirmalya Roy","orcid":"https://orcid.org/0000-0003-4827-3393"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nirmalya Roy","raw_affiliation_strings":["University of Maryland,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56295883,"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":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.8108999729156494,"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":0.8108999729156494,"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/T10237","display_name":"Cryptography and Data Security","score":0.020600000396370888,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.015399999916553497,"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/quantization","display_name":"Quantization (signal processing)","score":0.5194000005722046},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4763999879360199},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4569999873638153},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2816999852657318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7017999887466431},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4023999869823456},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38830000162124634},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34279999136924744},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/percom67906.2026.11524552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/percom67906.2026.11524552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Pervasive Computing and Communications (PerCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1987888496","https://openalex.org/W2963351448","https://openalex.org/W2963470657","https://openalex.org/W2963691377","https://openalex.org/W2990659535","https://openalex.org/W3124360785","https://openalex.org/W3176482836","https://openalex.org/W3176639943","https://openalex.org/W3209598599","https://openalex.org/W4214493665","https://openalex.org/W4285815152","https://openalex.org/W4317926941","https://openalex.org/W4317926962","https://openalex.org/W4382239439","https://openalex.org/W4384788088","https://openalex.org/W4385567528","https://openalex.org/W4385805175","https://openalex.org/W4401856677","https://openalex.org/W4406650295","https://openalex.org/W7133245369"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"enables":[3],"collaborative":[4],"machine":[5],"learning":[6],"across":[7,56,145],"decentralized":[8],"devices":[9,18],"and":[10,76,87,99],"data":[11],"sources,":[12],"but":[13],"resource":[14],"constraints":[15],"on":[16,96,113,218],"pervasive":[17,79,220],"necessitate":[19],"efficient":[20],"model":[21,155],"compression.":[22],"Existing":[23],"approaches,":[24],"such":[25],"as":[26],"quantization":[27,70,86,93,182],"for":[28,35,129,203],"on-device":[29],"training,":[30],"often":[31],"degrade":[32],"accuracy,":[33],"especially":[34],"classes":[36,131,150],"that":[37,64,84,148,160,181,196],"are":[38],"difficult":[39],"to":[40,43,72,105,125],"learn":[41],"due":[42],"imbalance,":[44],"poor-quality":[45],"samples,":[46],"or":[47],"inherent":[48],"complexity.":[49],"This":[50],"results":[51,193],"in":[52,78],"persistent":[53],"accuracy":[54,77,208],"gaps":[55],"classes.":[57,191],"We":[58,157,178],"propose":[59],"Fed-CASQ's":[60],"a":[61,137,163],"novel":[62,139],"framework":[63],"couples":[65],"class-aware":[66],"strategies":[67],"into":[68],"the":[69,114,135,185,200],"process":[71],"jointly":[73],"improve":[74],"efficiency":[75],"FL.":[80],"Unlike":[81],"prior":[82],"works":[83],"address":[85],"imbalance":[88,144],"separately,":[89],"Fed-CASQ":[90,161,197],"adaptively":[91],"selects":[92],"levels":[94],"based":[95],"device":[97],"resources":[98],"leverages":[100],"Layer-wise":[101],"Relevance":[102],"Propagation":[103],"(LRP)":[104],"assess":[106],"class-relevant":[107],"convolutional":[108],"neural":[109],"network":[110],"(CNN)":[111],"filters":[112],"client":[115],"side.":[116],"An":[117],"adaptive":[118],"weight":[119],"scaling":[120],"mechanism":[121],"is":[122],"then":[123],"applied":[124],"amplify":[126],"critical":[127],"information":[128],"low-accuracy":[130,204],"before":[132],"aggregation.":[133],"At":[134],"server,":[136],"complementary":[138],"aggregation":[140],"strategy":[141],"mitigates":[142],"global":[143],"clients,":[146],"ensuring":[147],"underperforming":[149],"receive":[151],"proportional":[152],"attention":[153],"during":[154],"updates.":[156],"theoretically":[158],"establish":[159,180],"achieves":[162],"convergence":[164],"rate":[165],"of":[166,187],"${\\mathcal{O}}\\left({\\frac{{\\kappa":[167],"*\\hat":[168,170],"\\sigma":[169],"\\delta":[171],"}}{{\\sqrt":[172],"T":[173],"}}}\\right)$":[174],"under":[175,188],"non-convex":[176],"settings.":[177],"empirically":[179],"directly":[183],"influences":[184],"performance":[186,201],"sampled":[189],"(minority)":[190],"Experimental":[192],"further":[194],"show":[195],"substantially":[198],"narrows":[199],"gap":[202],"classes,":[205],"improving":[206],"their":[207],"by":[209,215],"\u224830%,":[210],"while":[211],"reducing":[212],"training":[213],"latency":[214],"over":[216],"56%":[217],"resource-constrained":[219],"devices.":[221]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-23T00:00:00"}