{"id":"https://openalex.org/W3210101648","doi":"https://doi.org/10.1145/3486001.3486225","title":"Federated matched averaging with information-gain based parameter sampling","display_name":"Federated matched averaging with information-gain based parameter sampling","publication_year":2021,"publication_date":"2021-10-21","ids":{"openalex":"https://openalex.org/W3210101648","doi":"https://doi.org/10.1145/3486001.3486225","mag":"3210101648"},"language":"en","primary_location":{"id":"doi:10.1145/3486001.3486225","doi":"https://doi.org/10.1145/3486001.3486225","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486001.3486225","pdf_url":null,"source":{"id":"https://openalex.org/S7407089245","display_name":"International Conference on AI-ML Systems (AIMLSystems)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The First International Conference on AI-ML-Systems","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W3210101648"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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":null,"display_name":"Sharad Shukla","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sharad Shukla","raw_affiliation_strings":["Indian Institute of Technology Kanpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103180580","display_name":"Nisheeth Srivastava","orcid":"https://orcid.org/0000-0001-9272-8418","observed_orcids":["https://orcid.org/0000-0001-9272-8418"]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nisheeth Srivastava","raw_affiliation_strings":["Indian Institute of Technology Kanpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":0.3729,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.54976015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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":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":9.999999747378752e-05,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/federated-learning","display_name":"federated learning","score":0.9819999933242798},{"id":"https://openalex.org/keywords/information-gain","display_name":"information gain","score":0.8809999823570251},{"id":"https://openalex.org/keywords/parameter-sampling","display_name":"parameter sampling","score":0.8799999952316284},{"id":"https://openalex.org/keywords/communication-efficiency","display_name":"communication efficiency","score":0.9440000057220459},{"id":"https://openalex.org/keywords/edge-devices","display_name":"edge devices","score":0.7409999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8523703813552856},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8509018421173096},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7004779577255249},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6435270309448242},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6070791482925415},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48625314235687256},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4788667857646942},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45527005195617676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45478758215904236},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.42483559250831604},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40445783734321594},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13391047716140747},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1019144356250763},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3486001.3486225","doi":"https://doi.org/10.1145/3486001.3486225","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486001.3486225","pdf_url":null,"source":{"id":"https://openalex.org/S7407089245","display_name":"International Conference on AI-ML Systems (AIMLSystems)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The First International Conference on AI-ML-Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2095705004","https://openalex.org/W2108475251","https://openalex.org/W2151320232","https://openalex.org/W2222512263","https://openalex.org/W2535838896","https://openalex.org/W2541884796","https://openalex.org/W2785605868","https://openalex.org/W2810470036","https://openalex.org/W2902113386","https://openalex.org/W2912654452","https://openalex.org/W2913570153","https://openalex.org/W2914328083","https://openalex.org/W2941394876","https://openalex.org/W2946573451","https://openalex.org/W2971122887","https://openalex.org/W2983269934","https://openalex.org/W2995022099","https://openalex.org/W2996736801","https://openalex.org/W3021654819","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4319069175","https://openalex.org/W3216265618","https://openalex.org/W4388818404","https://openalex.org/W3203336515","https://openalex.org/W3046178819","https://openalex.org/W2996736801","https://openalex.org/W4281932789","https://openalex.org/W4399400854","https://openalex.org/W4321636655","https://openalex.org/W4408096838"],"abstract_inverted_index":{"Federated":[0],"learning":[1,72,95],"allows":[2],"edge":[3],"devices":[4],"to":[5,63],"learn":[6],"a":[7,39,47,70],"shared":[8],"global":[9],"model":[10,14,30],"from":[11],"the":[12,18,22,59],"client\u2019s":[13],"parameters":[15,31,62],"while":[16],"keeping":[17],"training":[19],"data":[20],"on":[21],"device.":[23],"However,":[24],"for":[25],"large":[26],"models,":[27],"transmitting":[28],"all":[29,67],"imposes":[32],"considerable":[33],"communication":[34,91],"costs,":[35],"which":[36],"can":[37],"be":[38,64],"significant":[40],"bottleneck":[41],"in":[42,69,93],"bandwidth-constrained":[43],"deployments.":[44],"We":[45],"present":[46],"federated":[48,71,94],"matched":[49],"averaging":[50],"algorithm":[51,88],"with":[52],"information-gain":[53],"based":[54],"sampling":[55],"that":[56,86],"considerably":[57],"reduces":[58,90],"number":[60],"of":[61],"sent":[65],"by":[66],"clients":[68],"paradigm.":[73],"Experiments":[74],"across":[75],"five":[76],"benchmark":[77],"datasets,":[78],"encompassing":[79],"symbolic,":[80],"image":[81],"and":[82],"audio":[83],"data,":[84],"suggest":[85],"our":[87],"significantly":[89],"overhead":[92],"settings,":[96],"without":[97],"reducing":[98],"classification":[99],"accuracy.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-11-08T00:00:00"}