{"id":"https://openalex.org/W4416251337","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227313","title":"Remembering Transformer for Continual Learning","display_name":"Remembering Transformer for Continual Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251337","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227313"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5041151881","display_name":"Yuwei Sun","orcid":"https://orcid.org/0000-0001-7315-8034"},"institutions":[{"id":"https://openalex.org/I4210123257","display_name":"Konya E\u011fitim ve Ara\u015ft\u0131rma Hastanesi","ror":"https://ror.org/020rayx20","country_code":"TR","type":"healthcare","lineage":["https://openalex.org/I4210123257"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Yuwei Sun","raw_affiliation_strings":["Araya Research"],"affiliations":[{"raw_affiliation_string":"Araya Research","institution_ids":["https://openalex.org/I4210123257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034050176","display_name":"Ippei Fujisawa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123257","display_name":"Konya E\u011fitim ve Ara\u015ft\u0131rma Hastanesi","ror":"https://ror.org/020rayx20","country_code":"TR","type":"healthcare","lineage":["https://openalex.org/I4210123257"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ippei Fujisawa","raw_affiliation_strings":["Araya Research"],"affiliations":[{"raw_affiliation_string":"Araya Research","institution_ids":["https://openalex.org/I4210123257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067775555","display_name":"Arthur Juliani","orcid":"https://orcid.org/0000-0002-1971-5167"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arthur Juliani","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063868203","display_name":"Jun Sakuma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Sakuma","raw_affiliation_strings":["RIKEN AIP"],"affiliations":[{"raw_affiliation_string":"RIKEN AIP","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049957600","display_name":"Ryota Kanai","orcid":"https://orcid.org/0000-0002-0186-2687"},"institutions":[{"id":"https://openalex.org/I4210123257","display_name":"Konya E\u011fitim ve Ara\u015ft\u0131rma Hastanesi","ror":"https://ror.org/020rayx20","country_code":"TR","type":"healthcare","lineage":["https://openalex.org/I4210123257"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ryota Kanai","raw_affiliation_strings":["Araya Research"],"affiliations":[{"raw_affiliation_string":"Araya Research","institution_ids":["https://openalex.org/I4210123257"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041151881"],"corresponding_institution_ids":["https://openalex.org/I4210123257"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19464182,"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":"9"},"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":0.7789000272750854,"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":0.7789000272750854,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05119999870657921,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.025599999353289604,"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/forgetting","display_name":"Forgetting","score":0.748199999332428},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7232000231742859},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40450000762939453},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.39739999175071716},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3896999955177307},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3222000002861023},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.3131999969482422}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.748199999332428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268999814987183},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7232000231742859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5752000212669373},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.532800018787384},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3222000002861023},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1997865285","https://openalex.org/W2104643304","https://openalex.org/W2150884987","https://openalex.org/W2424347275","https://openalex.org/W2473930607","https://openalex.org/W2554616628","https://openalex.org/W2560647685","https://openalex.org/W2791120355","https://openalex.org/W2895699061","https://openalex.org/W2964189064","https://openalex.org/W3007041883","https://openalex.org/W3015684125","https://openalex.org/W3048941751","https://openalex.org/W3106217498","https://openalex.org/W3178686235","https://openalex.org/W4221144379","https://openalex.org/W4221161784","https://openalex.org/W4285493813","https://openalex.org/W4292794834","https://openalex.org/W4312238419","https://openalex.org/W4318823481","https://openalex.org/W4319299931","https://openalex.org/W4402702936"],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"neural":[1],"networks":[2],"including":[3],"Transformers":[4],"encounter":[5],"the":[6,92,123],"catastrophic":[7],"forgetting":[8,156],"problem":[9],"during":[10],"sequential":[11],"task":[12,53,82,154,170],"learning,":[13],"where":[14,122],"learning":[15,49,190],"new":[16],"tasks":[17],"interferes":[18],"with":[19,180],"previously":[20],"learned":[21],"knowledge.":[22],"Existing":[23],"memory":[24,159],"replay":[25],"and":[26,52,146,158],"regularization":[27],"methods":[28,39,179],"cannot":[29],"effectively":[30],"eliminate":[31],"interference":[32],"among":[33],"different":[34],"tasks.":[35,191],"Soft":[36],"parameter":[37,108,182],"sharing":[38,109],"usually":[40],"necessitate":[41],"a":[42,76,99,119,185],"large":[43],"amount":[44],"of":[45,125,188],"additional":[46],"parameters":[47,127],"for":[48,58,80],"each":[50],"task,":[51],"identity":[54,171],"information":[55],"is":[56,128],"essential":[57],"leveraging":[59,69],"task-specific":[60,126],"parameters.":[61],"To":[62],"this":[63],"end,":[64],"we":[65,117,132],"propose":[66],"Remembering":[67,163],"Transformer":[68,164],"an":[70,134],"adapter":[71,135],"mixtures":[72],"architecture":[73],"enhanced":[74,181],"by":[75,153],"generative":[77,85],"routing":[78],"mechanism":[79],"efficient":[81],"retention.":[83],"In":[84,130],"routing,":[86],"input":[87],"samples":[88],"are":[89],"allocated":[90],"to":[91,138],"most":[93],"relevant":[94],"expert":[95],"adapters":[96],"based":[97,142],"on":[98,106,143],"reconstruction":[100],"loss.":[101],"Moreover,":[102],"unlike":[103],"existing":[104],"studies":[105],"soft":[107],"that":[110,162],"do":[111],"not":[112],"consider":[113],"model":[114],"capacity":[115],"limitations,":[116],"investigate":[118],"challenging":[120],"setting":[121],"number":[124],"constrained.":[129],"particular,":[131],"devise":[133],"fusion":[136],"strategy":[137],"aggregate":[139],"resembling":[140],"experts":[141],"similarity":[144],"matching":[145],"knowledge":[147,167],"distillation.":[148],"Extensive":[149],"empirical":[150],"results":[151],"measured":[152],"accuracy,":[155],"rate,":[157],"footprint,":[160],"demonstrate":[161],"significantly":[165],"enhances":[166],"retention":[168],"without":[169],"information.":[172],"The":[173],"proposed":[174],"method":[175],"surpasses":[176],"various":[177],"conventional":[178],"efficiency":[183],"in":[184],"broad":[186],"range":[187],"incremental":[189]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}