{"id":"https://openalex.org/W7155564697","doi":"https://doi.org/10.48550/arxiv.2604.21046","title":"JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning","display_name":"JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155564697","doi":"https://doi.org/10.48550/arxiv.2604.21046"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.21046","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21046","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.21046","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120499275","display_name":"Ali Aghababaei-Harandi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aghababaei-Harandi, Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005083101","display_name":"Aude Sportisse","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sportisse, Aude","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134544320","display_name":"Massih-Reza Amini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amini, Massih-Reza","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/T12535","display_name":"Machine Learning and Data Classification","score":0.37299999594688416,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.37299999594688416,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.24650000035762787,"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":0.07850000262260437,"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/regularization","display_name":"Regularization (linguistics)","score":0.5527999997138977},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5372999906539917},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4124000072479248},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4011000096797943},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3910999894142151},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.35370001196861267},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.35100001096725464},{"id":"https://openalex.org/keywords/probably-approximately-correct-learning","display_name":"Probably approximately correct learning","score":0.3384999930858612},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.3352000117301941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6345000267028809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.621999979019165},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5444999933242798},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5372999906539917},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.35100001096725464},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.3384999930858612},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C50292564","wikidata":"https://www.wikidata.org/wiki/Q2462783","display_name":"Computational learning theory","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.21046","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21046","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.21046","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21046","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":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5487686395645142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Semi-supervised":[0],"learning":[1,21,71],"has":[2],"emerged":[3],"as":[4],"a":[5,107,136,159,178],"powerful":[6],"paradigm":[7,108],"for":[8],"leveraging":[9],"large":[10],"amounts":[11],"of":[12,19,120,175,195],"unlabeled":[13],"data":[14,25,47],"to":[15,68,80,98,231],"improve":[16],"the":[17,70,88,128,165,193,209,222,226],"performance":[18],"machine":[20],"models":[22],"when":[23],"labeled":[24],"are":[26],"scarce.":[27],"Among":[28],"existing":[29,214],"approaches,":[30],"methods":[31,58],"derived":[32,182],"from":[33,90,110,183],"FixMatch":[34],"have":[35],"achieved":[36],"state-of-the-art":[37],"results":[38],"in":[39,150,170],"image":[40],"classification":[41],"by":[42,76,127],"combining":[43],"weak":[44],"and":[45,204],"strong":[46,54],"augmentations":[48],"with":[49,61,177],"confidence-based":[50],"pseudo-labeling.":[51],"Despite":[52],"their":[53],"empirical":[55],"performance,":[56],"these":[57],"typically":[59],"struggle":[60],"two":[62],"critical":[63],"bottlenecks:":[64],"majority":[65],"classes":[66],"tend":[67],"dominate":[69],"process,":[72],"which":[73],"is":[74,125],"amplified":[75],"incorrect":[77],"pseudo-labels,":[78],"leading":[79],"biased":[81],"models.":[82],"Furthermore,":[83],"noisy":[84],"early":[85],"pseudo-labels":[86],"prevent":[87],"model":[89],"forming":[91],"clear":[92],"decision":[93],"boundaries,":[94],"requiring":[95],"prolonged":[96],"training":[97,161],"learn":[99],"informative":[100],"representation.":[101],"In":[102,216],"this":[103,155],"paper,":[104],"we":[105,157,206],"introduce":[106],"shift":[109],"conventional":[111],"logical":[112],"output":[113],"threshold":[114],"base,":[115],"toward":[116],"an":[117,146,172],"explicit":[118],"shaping":[119],"geometric":[121],"representations.":[122],"Our":[123,185],"approach":[124],"inspired":[126],"recently":[129],"proposed":[130,186,210],"Latent-Euclidean":[131],"Joint-Embedding":[132],"Predictive":[133],"Architectures":[134],"(LeJEPA),":[135],"theoretically":[137],"grounded":[138],"framework":[139],"asserting":[140],"that":[141,163,208],"meaningful":[142],"representations":[143,190],"should":[144],"exhibit":[145],"isotropic":[147],"Gaussian":[148],"structure":[149],"latent":[151],"space.":[152],"Building":[153],"on":[154,201],"principle,":[156],"propose":[158],"new":[160],"objective":[162],"combines":[164],"classical":[166],"semi-supervised":[167],"loss":[168],"used":[169],"FlexMatch,":[171],"adaptive":[173],"extension":[174],"FixMatch,":[176],"latent-space":[179],"regularization":[180],"term":[181],"LeJEPA.":[184],"approach,":[187],"encourages":[188],"well-structured":[189],"while":[191],"preserving":[192],"advantages":[194],"pseudo-labeling":[196],"strategies.":[197],"Through":[198],"extensive":[199],"experiments":[200],"CIFAR-100,":[202],"STL-10":[203],"Tiny-ImageNet,":[205],"demonstrate":[207],"method":[211,219],"consistently":[212],"outperforms":[213],"baselines.":[215],"addition,":[217],"our":[218],"significantly":[220],"accelerates":[221],"convergence,":[223],"drastically":[224],"reducing":[225],"overall":[227],"computational":[228],"cost":[229],"compared":[230],"standard":[232],"FixMatch-based":[233],"pipelines.":[234]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-25T00:00:00"}