{"id":"https://openalex.org/W4320024194","doi":"https://doi.org/10.1109/bigdata55660.2022.10021082","title":"Differentially Private Federated Continual Learning with Heterogeneous Cohort Privacy","display_name":"Differentially Private Federated Continual Learning with Heterogeneous Cohort Privacy","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024194","doi":"https://doi.org/10.1109/bigdata55660.2022.10021082"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10021082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10021082","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE International Conference on Big Data (Big Data)","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/A5013859689","display_name":"Ajesh Koyatan Chathoth","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ajesh Koyatan Chathoth","raw_affiliation_strings":["University of Pittsburgh,Pittsburgh,PA,USA","University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076934411","display_name":"Clark P Necciai","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clark P Necciai","raw_affiliation_strings":["University of Pittsburgh,Pittsburgh,PA,USA","University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015390901","display_name":"Abhyuday Jagannatha","orcid":"https://orcid.org/0000-0001-5334-5481"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhyuday Jagannatha","raw_affiliation_strings":["University of Massachusetts Amherst,Amherst,MA,USA","University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst,Amherst,MA,USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100650753","display_name":"Stephen Lee","orcid":"https://orcid.org/0000-0001-9022-4259"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Lee","raw_affiliation_strings":["University of Pittsburgh,Pittsburgh,PA,USA","University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013859689"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":1.1507,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80855462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5682","last_page":"5691"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9628000259399414,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.947700023651123,"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/differential-privacy","display_name":"Differential privacy","score":0.896748423576355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7916833162307739},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.6554152965545654},{"id":"https://openalex.org/keywords/private-information-retrieval","display_name":"Private information retrieval","score":0.5608899593353271},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5494073629379272},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4878530502319336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3763164281845093},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3601536154747009},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24146246910095215},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2164645791053772}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.896748423576355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916833162307739},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.6554152965545654},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.5608899593353271},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5494073629379272},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4878530502319336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3763164281845093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3601536154747009},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24146246910095215},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2164645791053772},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10021082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10021082","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W768808963","https://openalex.org/W2053637704","https://openalex.org/W2113792377","https://openalex.org/W2460676686","https://openalex.org/W2473418344","https://openalex.org/W2535690855","https://openalex.org/W2560647685","https://openalex.org/W2566079294","https://openalex.org/W2594311007","https://openalex.org/W2734314755","https://openalex.org/W2766255512","https://openalex.org/W2788502731","https://openalex.org/W2807006176","https://openalex.org/W2810715221","https://openalex.org/W2911527057","https://openalex.org/W2911978475","https://openalex.org/W3020949888","https://openalex.org/W3021931813","https://openalex.org/W3038022836","https://openalex.org/W3118608800","https://openalex.org/W4205228770","https://openalex.org/W4294106961","https://openalex.org/W4295883599","https://openalex.org/W4298221930","https://openalex.org/W4301163820","https://openalex.org/W4318619660","https://openalex.org/W6622370708","https://openalex.org/W6663928093","https://openalex.org/W6720711607","https://openalex.org/W6728757088","https://openalex.org/W6741217325","https://openalex.org/W6745253412","https://openalex.org/W6746720608","https://openalex.org/W6748544737","https://openalex.org/W6752029299","https://openalex.org/W6752985224","https://openalex.org/W6758281836","https://openalex.org/W6759238902","https://openalex.org/W6771536673","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W4286891119","https://openalex.org/W4320024194","https://openalex.org/W2963224083","https://openalex.org/W4313531105","https://openalex.org/W3119117338","https://openalex.org/W4328027212","https://openalex.org/W3101456894","https://openalex.org/W3118810630","https://openalex.org/W3035174002","https://openalex.org/W3171910014"],"abstract_inverted_index":{"Differential":[0],"privacy":[1,18,26,35,52,77,116,139],"in":[2,33,145],"federated":[3],"learning":[4],"has":[5],"emerged":[6],"as":[7],"a":[8,46],"promising":[9],"solution":[10],"for":[11,75],"big":[12],"data":[13,55,82],"applications":[14],"to":[15,107,137],"achieve":[16],"strong":[17],"guarantees.":[19],"While":[20],"prior":[21],"work":[22],"assumes":[23],"that":[24,64,127],"the":[25,65,81,109],"requirements":[27,36,53],"are":[28],"homogeneous":[29],"across":[30,39,58],"all":[31],"clients,":[32],"practice,":[34],"can":[37],"differ":[38,57],"clients.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,90],"introduce":[45],"cohort-based":[47],"(\u03f5,":[48],"\u03b4)-DP":[49],"framework":[50],"where":[51],"and":[54,85,103,125],"distribution":[56],"these":[59],"client":[60],"cohorts.":[61],"We":[62,118],"show":[63,126],"performance":[66,111],"of":[67,112],"existing":[68],"differentially":[69],"private":[70],"stochastic":[71],"algorithms":[72],"degrade":[73],"significantly":[74,149],"heterogeneous":[76,115],"scenarios,":[78],"especially":[79],"when":[80],"is":[83],"non-independent":[84],"identically":[86],"distributed":[87],"(non-iid).":[88],"Moreover,":[89],"propose":[91],"two":[92],"novel":[93],"continual":[94],"learning-based":[95],"DP":[96],"training":[97,146],"methods":[98],"\u2014":[99,106],"DP-Synaptic":[100],"intelligence":[101],"(DP-SI)":[102],"DP-Rehearsal":[104],"(DP-R)":[105],"improve":[108],"model":[110],"cohorts":[113],"with":[114],"budgets.":[117],"evaluate":[119],"our":[120,128,134],"approach":[121,135],"on":[122],"real":[123],"datasets":[124],"techniques":[129],"outperform":[130],"baseline":[131],"techniques.":[132],"Furthermore,":[133],"adapts":[136],"post-hoc":[138],"budget":[140],"relaxations,":[141],"providing":[142],"greater":[143],"flexibility":[144],"models":[147],"without":[148],"impacting":[150],"performance.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}