{"id":"https://openalex.org/W7138445622","doi":"https://doi.org/10.48550/arxiv.2603.15263","title":"IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning","display_name":"IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7138445622","doi":"https://doi.org/10.48550/arxiv.2603.15263"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.15263","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15263","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.2603.15263","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129658864","display_name":"Konstantinos Almpanakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Almpanakis, Konstantinos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038898203","display_name":"Anna Kreshuk","orcid":"https://orcid.org/0000-0003-1334-6388"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kreshuk, Anna","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":0.8252999782562256,"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":0.8252999782562256,"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":0.037700001150369644,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.029600000008940697,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7041000127792358},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.5691999793052673},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5641000270843506},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5630999803543091},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5378999710083008},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4796000123023987},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.47429999709129333},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4562999904155731}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7041000127792358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6646000146865845},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.5691999793052673},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5641000270843506},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5630999803543091},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5378999710083008},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4399999976158142},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3472999930381775},{"id":"https://openalex.org/C2776043813","wikidata":"https://www.wikidata.org/wiki/Q1759113","display_name":"Batch production","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2741999924182892},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2671999931335449}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.15263","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15263","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.2603.15263","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15263","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":"Quality Education","score":0.503394365310669,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"has":[3],"revolutionized":[4],"representation":[5,39],"learning,":[6],"with":[7],"Joint-Embedding":[8],"Architectures":[9],"(JEAs)":[10],"emerging":[11],"as":[12,54,186],"an":[13,104],"effective":[14],"approach":[15],"for":[16],"capturing":[17],"semantic":[18],"features.":[19],"Existing":[20],"JEAs":[21,185],"rely":[22],"on":[23],"implicit":[24],"or":[25,33],"explicit":[26,105],"batch":[27,48,83,90,116,127,133,187],"interaction":[28],"--":[29,36],"via":[30],"negative":[31],"sampling":[32],"statistical":[34],"regularization":[35],"to":[37,117,132,156,162],"prevent":[38],"collapse.":[40],"This":[41,108],"reliance":[42],"becomes":[43],"problematic":[44],"in":[45,175,183],"regimes":[46],"where":[47,58],"sizes":[49,188],"must":[50],"be":[51],"small,":[52],"such":[53],"high-dimensional":[55],"scientific":[56],"data,":[57],"memory":[59],"constraints":[60],"and":[61,139,147,158],"class":[62,164],"imbalance":[63],"make":[64],"large,":[65],"well-balanced":[66],"batches":[67],"infeasible.":[68],"We":[69],"introduce":[70],"IConE":[71,92,143,170],"(Instance-Contrasted":[72],"Embeddings),":[73],"a":[74,94,118],"framework":[75],"that":[76,169],"decouples":[77],"collapse":[78,181],"prevention":[79],"from":[80,113],"the":[81,110,114,151,176,180],"training":[82,124],"size.":[84],"Rather":[85],"than":[86],"enforcing":[87],"diversity":[88,106],"through":[89],"statistics,":[91],"maintains":[93],"global":[95],"set":[96],"of":[97],"learnable":[98],"auxiliary":[99],"instance":[100],"embeddings":[101],"regularized":[102],"by":[103],"objective.":[107],"transfers":[109],"anti-collapse":[111],"mechanism":[112],"transient":[115],"dataset-level":[119],"embedding":[120],"space,":[121],"allowing":[122],"stable":[123],"even":[125],"when":[126],"statistics":[128],"are":[129],"unreliable,":[130],"down":[131],"size":[134],"1.":[135],"Across":[136],"diverse":[137],"2D":[138],"3D":[140],"biomedical":[141],"modalities,":[142],"outperforms":[144],"strong":[145],"contrastive":[146],"non-contrastive":[148],"baselines":[149],"throughout":[150],"small-batch":[152],"regime":[153],"(from":[154],"B=1":[155],"B=64)":[157],"demonstrates":[159],"marked":[160],"robustness":[161],"severe":[163],"imbalance.":[165],"Geometric":[166],"analysis":[167],"shows":[168],"preserves":[171],"high":[172],"intrinsic":[173],"dimensionality":[174],"learned":[177],"representations,":[178],"preventing":[179],"observed":[182],"existing":[184],"shrink.":[189]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-18T00:00:00"}