{"id":"https://openalex.org/W3208999853","doi":"https://doi.org/10.48550/arxiv.2110.12292","title":"Federated Multiple Label Hashing (FedMLH): Communication Efficient Federated Learning on Extreme Classification Tasks","display_name":"Federated Multiple Label Hashing (FedMLH): Communication Efficient Federated Learning on Extreme Classification Tasks","publication_year":2021,"publication_date":"2021-10-23","ids":{"openalex":"https://openalex.org/W3208999853","doi":"https://doi.org/10.48550/arxiv.2110.12292","mag":"3208999853"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2110.12292","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.12292","pdf_url":"https://arxiv.org/pdf/2110.12292","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.12292","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dai, Zhenwei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Zhenwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dun, Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dun, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102770278","display_name":"Yuxin Tang","orcid":"https://orcid.org/0009-0000-2401-5360","observed_orcids":["https://orcid.org/0009-0000-2401-5360"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024280658","display_name":"Anastasios Kyrillidis","orcid":"https://orcid.org/0000-0003-1954-8730","observed_orcids":["https://orcid.org/0000-0003-1954-8730"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyrillidis, Anastasios","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024993683","display_name":"Anshumali Shrivastava","orcid":"https://orcid.org/0000-0002-5042-2856","observed_orcids":["https://orcid.org/0000-0002-5042-2856"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shrivastava, Anshumali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00019999999494757503,"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":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"}}],"keywords":[{"id":"https://openalex.org/keywords/federated-learning","display_name":"federated learning","score":0.9789999723434448},{"id":"https://openalex.org/keywords/communication-efficiency","display_name":"communication efficiency","score":0.7300000190734863},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.5460000038146973},{"id":"https://openalex.org/keywords/non-iid-data","display_name":"non-IID data","score":0.7929999828338623},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.9570000171661377},{"id":"https://openalex.org/keywords/data-heterogeneity","display_name":"data heterogeneity","score":0.5879999995231628},{"id":"https://openalex.org/keywords/user-recommendation","display_name":"user recommendation","score":0.6330000162124634},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.5059999823570251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8334685564041138},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7926936149597168},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7560195922851562},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6292133927345276},{"id":"https://openalex.org/C133667856","wikidata":"https://www.wikidata.org/wiki/Q5439682","display_name":"Feature hashing","level":5,"score":0.585884153842926},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47043249011039734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593951404094696},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4591481387615204},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3460164964199066},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.29376208782196045},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.09434112906455994},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2110.12292","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.12292","pdf_url":"https://arxiv.org/pdf/2110.12292","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2110.12292","doi":"https://doi.org/10.48550/arxiv.2110.12292","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.12292","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.12292","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.12292","pdf_url":"https://arxiv.org/pdf/2110.12292","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3208999853.pdf","grobid_xml":"https://content.openalex.org/works/W3208999853.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1781770377","https://openalex.org/W2061873838","https://openalex.org/W2106854428","https://openalex.org/W2115119296","https://openalex.org/W2541884796","https://openalex.org/W2788125153","https://openalex.org/W2807006176","https://openalex.org/W2900182564","https://openalex.org/W2904760378","https://openalex.org/W2914328083","https://openalex.org/W2951440817","https://openalex.org/W2963318081","https://openalex.org/W2964032223","https://openalex.org/W2982392466","https://openalex.org/W2996442797","https://openalex.org/W3006555759","https://openalex.org/W3037674069","https://openalex.org/W3109094166","https://openalex.org/W3153137927","https://openalex.org/W4287207694"],"related_works":["https://openalex.org/W4396909891","https://openalex.org/W4283068112","https://openalex.org/W3104895314","https://openalex.org/W4322717171","https://openalex.org/W7170361479","https://openalex.org/W4386736771","https://openalex.org/W4406458452","https://openalex.org/W4386214687","https://openalex.org/W4389111278","https://openalex.org/W4408167978"],"abstract_inverted_index":{"Federated":[0],"learning":[1,10,79],"enables":[2],"many":[3],"local":[4,16,33,50],"devices":[5],"to":[6,59,65,96,135,142,149,158,168,180],"train":[7],"a":[8,25,60],"deep":[9],"model":[11,27,51,56,92,139],"jointly":[12],"without":[13],"sharing":[14],"the":[15,30,66,75,87,91,97,138,174],"data.":[17],"Currently,":[18],"most":[19,36],"of":[20,32,37,99],"federated":[21,78,126,175,181],"training":[22,39],"schemes":[23,40],"learns":[24],"global":[26],"by":[28],"averaging":[29,55],"parameters":[31,57],"models.":[34],"However,":[35],"these":[38],"suffer":[41],"from":[42,47],"high":[43],"communication":[44,85,146],"cost":[45,147],"resulted":[46],"transmitting":[48],"full":[49],"parameters.":[52],"Moreover,":[53],"directly":[54],"leads":[58],"significant":[61,154],"performance":[62],"degradation,":[63],"due":[64],"class-imbalanced":[67],"non-iid":[68],"data":[69,116],"on":[70,117,173],"different":[71,118],"devices.":[72,119],"Especially":[73],"for":[74,171],"real":[76],"life":[77],"tasks":[80,178],"involving":[81],"extreme":[82,103,176],"classification,":[83],"(1)":[84],"becomes":[86],"main":[88],"bottleneck":[89],"since":[90],"size":[93,140],"increases":[94],"proportionally":[95],"number":[98],"output":[100],"classes;":[101],"(2)":[102],"classification":[104,177],"(such":[105],"as":[106],"user":[107],"recommendation)":[108],"normally":[109],"have":[110],"extremely":[111],"imbalanced":[112],"classes":[113],"and":[114,152,163],"heterogeneous":[115],"To":[120],"overcome":[121],"this":[122],"problem,":[123],"we":[124],"propose":[125],"multiple":[127],"label":[128,133],"hashing":[129,134],"(FedMLH),":[130],"which":[131],"leverages":[132],"simultaneously":[136],"reduce":[137],"(up":[141,148,157,167],"3.40X":[143],"decrease)":[144,151],"with":[145],"18.75X":[150],"achieves":[153],"better":[155],"accuracy":[156,161],"35.5%}":[159],"relative":[160],"improvement)":[162],"faster":[164],"convergence":[165],"rate":[166],"5.5X":[169],"increase)":[170],"free":[172],"compared":[179],"average":[182],"algorithm.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-11-08T00:00:00"}