{"id":"https://openalex.org/W7143497364","doi":"https://doi.org/10.48550/arxiv.2603.26192","title":"HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning","display_name":"HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7143497364","doi":"https://doi.org/10.48550/arxiv.2603.26192"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.26192","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26192","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2603.26192","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130987616","display_name":"Xuerui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Xuerui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130952453","display_name":"Xuehao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xuehao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122852808","display_name":"Zhan Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Zhan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130925617","display_name":"Linglan Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Linglan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130948399","display_name":"Ziyue Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ziyue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654679","display_name":"Xinmin Zhang","orcid":"https://orcid.org/0000-0002-4761-3969"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xinmin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056181989","display_name":"Zhihuan Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Zhihuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5131001245","display_name":"Yu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5130987616"],"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":0.8626000285148621,"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":0.8626000285148621,"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":0.0284000001847744,"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/T13553","display_name":"Age of Information Optimization","score":0.009100000374019146,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.652999997138977},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"Lifelong learning","score":0.6496000289916992},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.645799994468689},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6190999746322632},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.46209999918937683},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.45969998836517334},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42500001192092896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760200023651123},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.652999997138977},{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.6496000289916992},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.645799994468689},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6190999746322632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6140999794006348},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5264000296592712},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.45969998836517334},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C30703548","wikidata":"https://www.wikidata.org/wiki/Q1757673","display_name":"Sobel operator","level":5,"score":0.34470000863075256},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C47431972","wikidata":"https://www.wikidata.org/wiki/Q3045948","display_name":"ELECTRE","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.26192","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26192","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.26192","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26192","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Lifelong":[0],"learning":[1,38,59,162],"aims":[2],"to":[3,79,146],"preserve":[4],"knowledge":[5,12,82,126],"acquired":[6],"from":[7,13,62],"previous":[8],"tasks":[9,28,41],"while":[10],"incorporating":[11],"a":[14,103,141,155],"sequence":[15,68],"of":[16,26,37,46,69,99,151],"new":[17,186],"tasks.":[18],"However,":[19],"most":[20],"prior":[21],"work":[22],"explores":[23],"only":[24,30],"streams":[25],"homogeneous":[27],"(\\textit{e.g.},":[29],"classification":[31],"tasks)":[32],"and":[33,75,105,154],"neglects":[34],"the":[35,66,76,90,97,113,148,169,176],"scenario":[36],"across":[39],"heterogeneous":[40,58,81,125],"that":[42,121,160,175],"possess":[43],"different":[44,72,84],"structures":[45],"outputs.":[47],"In":[48],"this":[49,53,109,185],"work,":[50],"we":[51,92,111],"formalize":[52],"broader":[54],"setting":[55],"as":[56],"lifelong":[57,64],"(LHL).":[60],"Departing":[61],"conventional":[63],"learning,":[65],"task":[67,73],"LHL":[70,95],"spans":[71],"types,":[74],"learner":[77],"needs":[78],"retain":[80],"for":[83],"output":[85],"space":[86],"structures.":[87],"To":[88,108],"instantiate":[89],"LHL,":[91],"focus":[93],"on":[94,163],"in":[96,129,184],"context":[98],"dense":[100],"prediction":[101,152],"(LHL4DP),":[102],"realistic":[104],"challenging":[106],"scenario.":[107,187],"end,":[110],"propose":[112],"Heterogeneity-Aware":[114],"Distillation":[115],"(HAD)":[116],"method,":[117],"an":[118],"exemplar-free":[119],"approach":[120],"preserves":[122],"previously":[123],"gained":[124],"by":[127],"self-distillation":[128],"each":[130],"training":[131],"phase.":[132],"The":[133],"proposed":[134,177],"HAD":[135,178],"comprises":[136],"two":[137],"complementary":[138],"components,":[139],"including":[140],"distribution-balanced":[142],"heterogeneity-aware":[143,157],"distillation":[144,158],"loss":[145,159],"alleviate":[147],"global":[149],"imbalance":[150],"distribution":[153],"salience-guided":[156],"concentrates":[161],"informative":[164],"edge":[165],"pixels":[166],"extracted":[167],"with":[168],"Sobel":[170],"operator.":[171],"Extensive":[172],"experiments":[173],"demonstrate":[174],"method":[179],"significantly":[180],"outperforms":[181],"existing":[182],"methods":[183]},"counts_by_year":[],"updated_date":"2026-03-31T06:07:48.031334","created_date":"2026-03-31T00:00:00"}