{"id":"https://openalex.org/W7140299933","doi":"https://doi.org/10.48550/arxiv.2603.23436","title":"Similarity-Aware Mixture-of-Experts for Data-Efficient Continual Learning","display_name":"Similarity-Aware Mixture-of-Experts for Data-Efficient Continual Learning","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140299933","doi":"https://doi.org/10.48550/arxiv.2603.23436"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.23436","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23436","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.23436","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126362606","display_name":"Connor Mclaughlin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mclaughlin, Connor","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130580246","display_name":"Nigel Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Nigel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130564468","display_name":"Lili Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Lili","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5126362606"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9315000176429749,"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":0.9315000176429749,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.010900000110268593,"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/T11448","display_name":"Face recognition and analysis","score":0.004399999976158142,"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/task","display_name":"Task (project management)","score":0.6628000140190125},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5719000101089478},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4957999885082245},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4593999981880188},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4108999967575073},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.36800000071525574},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32829999923706055},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.31700000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443000078201294},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6628000140190125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6121000051498413},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5703999996185303},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4593999981880188},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4108999967575073},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.23436","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23436","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.23436","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23436","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Machine":[0],"learning":[1,44],"models":[2,133],"often":[3],"need":[4],"to":[5,7,13],"adapt":[6],"new":[8,183],"data":[9,39,91,205,210],"after":[10],"deployment":[11],"due":[12],"structured":[14],"or":[15,41],"unstructured":[16,109],"real-world":[17],"dynamics.":[18],"The":[19,155,167],"Continual":[20],"Learning":[21],"(CL)":[22],"framework":[23,130],"enables":[24],"continuous":[25],"model":[26],"adaptation,":[27],"but":[28],"most":[29],"existing":[30],"approaches":[31],"either":[32],"assume":[33],"each":[34,58],"task":[35,59,110,171,192],"contains":[36,143],"sufficiently":[37],"many":[38],"samples":[40,172],"that":[42,134,216],"the":[43,53,88,106,121,201],"tasks":[45,66],"are":[46],"non-overlapping.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,124],"address":[52,120],"more":[54,82],"general":[55,78,97],"setting":[56,79],"where":[57],"may":[60,67],"have":[61],"a":[62,74],"limited":[63],"dataset,":[64],"and":[65,99,151,180,212,222],"overlap":[68],"in":[69,115,200],"an":[70,126],"arbitrary":[71],"manner":[72],"without":[73],"priori":[75],"knowledge.":[76],"This":[77],"is":[80,223],"substantially":[81],"challenging":[83],"for":[84],"two":[85,144],"reasons.":[86],"On":[87,105],"one":[89],"hand,":[90,108],"scarcity":[92],"necessitates":[93],"effective":[94],"contextualization":[95],"of":[96,203],"knowledge":[98,101,117],"efficient":[100],"transfer":[102],"across":[103,208],"tasks.":[104,140],"other":[107],"overlapping":[111],"can":[112],"easily":[113],"result":[114],"negative":[116,197],"transfer.":[118],"To":[119],"above":[122],"challenges,":[123],"propose":[125],"adaptive":[127],"mixture-of-experts":[128],"(MoE)":[129],"over":[131,165],"pre-trained":[132],"progressively":[135],"establishes":[136],"similarity":[137,214],"awareness":[138],"among":[139],"Our":[141],"design":[142,188],"innovative":[145],"algorithmic":[146],"components:":[147],"incremental":[148],"global":[149],"pooling":[150],"instance-wise":[152],"prompt":[153,158,163],"masking.":[154],"former":[156],"mitigates":[157],"association":[159],"noise":[160],"through":[161],"gradual":[162],"introduction":[164],"time.":[166],"latter":[168],"decomposes":[169],"incoming":[170],"into":[173],"those":[174,181],"aligning":[175],"with":[176],"current":[177],"prompts":[178,184],"(in-distribution)":[179],"requiring":[182],"(out-of-distribution).":[185],"Together,":[186],"our":[187,217],"strategically":[189],"leverages":[190],"potential":[191],"overlaps":[193],"while":[194],"actively":[195],"preventing":[196],"mutual":[198],"interference":[199],"presence":[202],"per-task":[204],"scarcity.":[206],"Experiments":[207],"varying":[209],"volumes":[211],"inter-task":[213],"show":[215],"method":[218],"enhances":[219],"sample":[220],"efficiency":[221],"broadly":[224],"applicable.":[225]},"counts_by_year":[],"updated_date":"2026-03-26T06:10:45.909354","created_date":"2026-03-26T00:00:00"}