{"id":"https://openalex.org/W7154106884","doi":"https://doi.org/10.48550/arxiv.2604.08617","title":"From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity","display_name":"From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7154106884","doi":"https://doi.org/10.48550/arxiv.2604.08617"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.08617","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08617","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.08617","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133546387","display_name":"Zhuang Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Zhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069806977","display_name":"Ying-Peng Tang","orcid":"https://orcid.org/0000-0003-1529-9714"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Ying-Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133525742","display_name":"Lei Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133517071","display_name":"Guoqing Chao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao, Guoqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133495163","display_name":"Lei Wu","orcid":"https://orcid.org/0009-0007-7054-6542"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133521113","display_name":"Han Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133509872","display_name":"Xiangxu Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Xiangxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.8971999883651733,"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":0.8971999883651733,"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/T11448","display_name":"Face recognition and analysis","score":0.0421999990940094,"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":0.004800000227987766,"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/robustness","display_name":"Robustness (evolution)","score":0.6865000128746033},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6287999749183655},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5752000212669373},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4325999915599823},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4219000041484833},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41339999437332153},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3935000002384186},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3874000012874603},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.3314000070095062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670000195503235},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6865000128746033},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5752000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4325999915599823},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41100001335144043},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3440000116825104},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C9996903","wikidata":"https://www.wikidata.org/wiki/Q1749235","display_name":"Cryptographic nonce","level":3,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.08617","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08617","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.08617","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08617","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":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7504387497901917}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Exemplar":[0],"replay":[1],"has":[2],"become":[3],"an":[4],"effective":[5],"strategy":[6],"for":[7,40],"mitigating":[8],"catastrophic":[9],"forgetting":[10],"in":[11],"federated":[12],"continual":[13,51],"learning":[14],"(FCL)":[15],"by":[16,103],"retaining":[17],"representative":[18],"samples":[19],"from":[20,154],"past":[21],"tasks.":[22,57],"Existing":[23],"studies":[24],"focus":[25],"on":[26],"designing":[27],"sample-importance":[28],"estimation":[29],"mechanisms":[30],"to":[31,126,167],"identify":[32],"information-rich":[33],"samples.":[34],"However,":[35],"they":[36],"typically":[37],"overlook":[38],"strategies":[39],"effectively":[41],"utilizing":[42],"the":[43,94,105,145,172],"selected":[44],"exemplars,":[45],"which":[46,72,119,157],"limits":[47],"their":[48,113],"performance":[49],"under":[50,175],"dynamic":[52],"heterogeneity":[53],"across":[54,84,124,137],"clients":[55,125],"and":[56,112,122,139,170],"To":[58],"address":[59],"this":[60,62],"issue,":[61],"paper":[63],"proposes":[64],"a":[65,129],"Federated":[66],"gEometry-Aware":[67],"correcTion":[68],"method,":[69],"termed":[70],"FEAT,":[71],"alleviates":[73],"imbalance-induced":[74],"representation":[75,142],"collapse":[76],"that":[77],"drags":[78],"rare-class":[79],"features":[80],"toward":[81,161],"frequent":[82],"classes":[83,169],"clients.":[85],"Specifically,":[86],"it":[87],"consists":[88],"of":[89],"two":[90],"key":[91],"modules:":[92],"1)":[93],"Geometric":[95,147],"Structure":[96],"Alignment":[97],"module":[98,149],"performs":[99],"structural":[100],"knowledge":[101],"distillation":[102],"aligning":[104],"pairwise":[106],"angular":[107],"similarities":[108],"between":[109],"feature":[110,155],"representations":[111],"corresponding":[114],"Equiangular":[115],"Tight":[116],"Frame":[117],"prototypes,":[118],"are":[120],"fixed":[121],"shared":[123],"serve":[127],"as":[128],"class-discriminative":[130],"reference":[131],"structure.":[132],"This":[133,164],"encourages":[134],"geometric":[135],"consistency":[136],"tasks":[138],"helps":[140],"mitigate":[141],"drift;":[143],"2)":[144],"Energy-based":[146],"Correction":[148],"removes":[150],"task-irrelevant":[151],"directional":[152],"components":[153],"embeddings,":[156],"reduces":[158],"prediction":[159],"bias":[160],"majority":[162],"classes.":[163],"improves":[165],"sensitivity":[166],"minority":[168],"enhances":[171],"model's":[173],"robustness":[174],"class-imbalanced":[176],"distributions.":[177]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-14T00:00:00"}