{"id":"https://openalex.org/W4312093837","doi":"https://doi.org/10.1162/neco_a_01560","title":"Dynamic Consolidation for Continual Learning","display_name":"Dynamic Consolidation for Continual Learning","publication_year":2022,"publication_date":"2022-12-22","ids":{"openalex":"https://openalex.org/W4312093837","doi":"https://doi.org/10.1162/neco_a_01560","pmid":"https://pubmed.ncbi.nlm.nih.gov/36543332"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_01560","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_01560","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100455129","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-1230-4007"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hang Li","raw_affiliation_strings":["McGill University, Montreal, Quebec H3A 0G4, Canada hang.li3@mail.mcgill.ca"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Quebec H3A 0G4, Canada hang.li3@mail.mcgill.ca","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410908","display_name":"Chen Ma","orcid":"https://orcid.org/0000-0001-7933-9813"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen Ma","raw_affiliation_strings":["City University of Hong Kong, Hong Kong SAR, China chenma@cityu.edu.hk"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong SAR, China chenma@cityu.edu.hk","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329966","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-6402-5034"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Xi Chen","raw_affiliation_strings":["McGill University, Montreal, Quebec H3A 0G4, Canada xi.chen11@mcgill.ca"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Quebec H3A 0G4, Canada xi.chen11@mcgill.ca","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100372152","display_name":"Xue Liu","orcid":"https://orcid.org/0000-0001-5252-3442"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Xue Liu","raw_affiliation_strings":["McGill University, Montreal, Quebec H3A 0G4, Canada xueliu@cs.mcgill.ca"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Quebec H3A 0G4, Canada xueliu@cs.mcgill.ca","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100329966","https://openalex.org/A5100372152","https://openalex.org/A5100455129"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.5305,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71654384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"35","issue":"2","first_page":"228","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9531999826431274,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9445000290870667,"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/consolidation","display_name":"Consolidation (business)","score":0.5211653709411621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48220622539520264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44814085960388184},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4003477096557617},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3222680687904358},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.321106493473053},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1849813461303711}],"concepts":[{"id":"https://openalex.org/C2776014549","wikidata":"https://www.wikidata.org/wiki/Q3050847","display_name":"Consolidation (business)","level":2,"score":0.5211653709411621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48220622539520264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44814085960388184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4003477096557617},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3222680687904358},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.321106493473053},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1849813461303711},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/neco_a_01560","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_01560","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:36543332","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36543332","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2116522068","https://openalex.org/W2194775991","https://openalex.org/W2335728318","https://openalex.org/W2473930607","https://openalex.org/W2554616628","https://openalex.org/W2560647685","https://openalex.org/W2604272474","https://openalex.org/W2612690371","https://openalex.org/W2782276075","https://openalex.org/W2804746922","https://openalex.org/W2939137134","https://openalex.org/W2963588172","https://openalex.org/W2964048876","https://openalex.org/W2964067969","https://openalex.org/W2981864462","https://openalex.org/W2990138404","https://openalex.org/W3030364939","https://openalex.org/W3148342934","https://openalex.org/W4236965008","https://openalex.org/W4319988532","https://openalex.org/W6684191040","https://openalex.org/W6687483927","https://openalex.org/W6703116779","https://openalex.org/W6730146409","https://openalex.org/W6738602802","https://openalex.org/W6741087337","https://openalex.org/W6741217325","https://openalex.org/W6746658061","https://openalex.org/W6762867720","https://openalex.org/W6763195353","https://openalex.org/W6764645560","https://openalex.org/W6768044712","https://openalex.org/W6771234588","https://openalex.org/W6778804409","https://openalex.org/W6779679106","https://openalex.org/W6793777737","https://openalex.org/W6805023924"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Training":[0],"deep":[1],"learning":[2,28],"models":[3],"from":[4,42],"a":[5,11,23,62,128],"stream":[6],"of":[7,78,89,96,131,153,201],"nonstationary":[8],"data":[9,183],"is":[10,106,110],"critical":[12],"problem":[13],"to":[14,17,32,40,100,138,158,170,197],"be":[15],"solved":[16],"achieve":[18],"general":[19],"artificial":[20],"intelligence.":[21],"As":[22],"promising":[24],"solution,":[25],"the":[26,38,47,72,76,79,86,90,93,102,113,124,132,140,147,151,154,159,166,174,192],"continual":[27],"(CL)":[29],"technique":[30],"aims":[31],"build":[33],"intelligent":[34],"systems":[35],"that":[36,187],"have":[37],"plasticity":[39],"learn":[41],"new":[43,65],"information":[44],"without":[45],"forgetting":[46],"previously":[48,103],"obtained":[49],"knowledge.":[50],"Unfortunately,":[51],"existing":[52,67],"CL":[53,68],"methods":[54,69],"face":[55],"two":[56],"nontrivial":[57],"limitations.":[58],"First,":[59],"when":[60],"updating":[61],"model":[63,73,160],"with":[64,127,173],"data,":[66,84],"usually":[70],"constrain":[71],"parameters":[74,80],"within":[75],"vicinity":[77,125],"optimized":[81],"for":[82,112],"old":[83],"limiting":[85],"exploration":[87],"ability":[88],"model;":[91],"second,":[92],"important":[94,133,148,167],"strength":[95,149,168],"each":[97],"parameter":[98,115,142,176],"(used":[99],"consolidate":[101],"learned":[104],"knowledge)":[105],"fixed":[107],"and":[108],"thus":[109],"suboptimal":[111],"dynamic":[114,175],"updates.":[116,177],"To":[117],"address":[118],"these":[119],"limitations,":[120],"we":[121,145,163,185],"first":[122],"relax":[123],"constraints":[126],"global":[129,155],"definition":[130],"strength,":[134],"which":[135],"allows":[136],"us":[137],"explore":[139],"full":[141],"space.":[143],"Specifically,":[144],"define":[146],"as":[150],"sensitivity":[152],"loss":[156],"function":[157],"parameters.":[161],"Moreover,":[162],"propose":[164],"adjusting":[165],"adaptively":[169],"align":[171],"it":[172],"Through":[178],"extensive":[179],"experiments":[180],"on":[181],"popular":[182],"sets,":[184],"demonstrate":[186],"our":[188],"proposed":[189],"method":[190],"outperforms":[191],"strong":[193],"baselines":[194],"by":[195],"up":[196],"24%":[198],"in":[199],"terms":[200],"average":[202],"accuracy.":[203]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
