{"id":"https://openalex.org/W7133239594","doi":"https://doi.org/10.52202/068431-1934","title":"Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods","display_name":"Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7133239594","doi":"https://doi.org/10.52202/068431-1934"},"language":"en","primary_location":{"id":"doi:10.52202/068431-1934","doi":"https://doi.org/10.52202/068431-1934","is_oa":false,"landing_page_url":"https://doi.org/10.52202/068431-1934","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 35","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.11508","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047293370","display_name":"Randall Balestriero","orcid":"https://orcid.org/0000-0002-5692-4187","observed_orcids":["https://orcid.org/0000-0002-5692-4187"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Randall Balestriero","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001226970","display_name":"Yann LeCun","orcid":"https://orcid.org/0000-0002-1992-2684","observed_orcids":["https://orcid.org/0000-0002-1992-2684"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yann Lecun","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":8.2222,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":{"value":0.983786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"26671","last_page":"26685"},"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":0.6298999786376953,"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":0.6298999786376953,"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/T10057","display_name":"Face and Expression Recognition","score":0.12700000405311584,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.07930000126361847,"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/self-supervised-learning","display_name":"self-supervised learning","score":0.9879999756813049},{"id":"https://openalex.org/keywords/spectral-embedding","display_name":"spectral embedding","score":0.8539999723434448},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.8429999947547913},{"id":"https://openalex.org/keywords/non-contrastive-learning","display_name":"non-contrastive learning","score":0.9819999933242798},{"id":"https://openalex.org/keywords/vicreg","display_name":"VICReg","score":0.9399999976158142},{"id":"https://openalex.org/keywords/simclr","display_name":"SimCLR","score":0.9980000257492065},{"id":"https://openalex.org/keywords/barlow-twins","display_name":"Barlow Twins","score":0.8830000162124634},{"id":"https://openalex.org/keywords/laplacian-eigenmaps","display_name":"Laplacian eigenmaps","score":0.8970000147819519},{"id":"https://openalex.org/keywords/multidimensional-scaling","display_name":"multidimensional scaling","score":0.9980000257492065},{"id":"https://openalex.org/keywords/linear-regime","display_name":"linear regime","score":0.625},{"id":"https://openalex.org/keywords/low-data-regimes","display_name":"low-data regimes","score":0.6140000224113464}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5799999833106995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5238999724388123},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3849000036716461},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/068431-1934","doi":"https://doi.org/10.52202/068431-1934","is_oa":false,"landing_page_url":"https://doi.org/10.52202/068431-1934","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 35","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.11508","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.11508","pdf_url":"https://arxiv.org/pdf/2205.11508","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2205.11508","doi":"https://doi.org/10.48550/arxiv.2205.11508","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2205.11508","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.11508","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.11508","pdf_url":"https://arxiv.org/pdf/2205.11508","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133239594.pdf","grobid_xml":"https://content.openalex.org/works/W7133239594.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2767321762","https://openalex.org/W2785325870","https://openalex.org/W2917551568","https://openalex.org/W2980471860","https://openalex.org/W3034893234","https://openalex.org/W3108949087","https://openalex.org/W3119521703","https://openalex.org/W3134652006","https://openalex.org/W3170863103","https://openalex.org/W3205065023","https://openalex.org/W3205069406","https://openalex.org/W4221144435","https://openalex.org/W4226002507","https://openalex.org/W4226253083","https://openalex.org/W4286695273","https://openalex.org/W4286909468","https://openalex.org/W4306155167","https://openalex.org/W7133192628","https://openalex.org/W7133242605"],"related_works":["https://openalex.org/W7126078644","https://openalex.org/W7133210510","https://openalex.org/W7164522874","https://openalex.org/W4281621864","https://openalex.org/W4379087908","https://openalex.org/W4361193944","https://openalex.org/W4415066491","https://openalex.org/W3131573008","https://openalex.org/W4312659823","https://openalex.org/W4400840545"],"abstract_inverted_index":{"Self-Supervised":[0],"Learning":[1],"(SSL)":[2],"surmises":[3],"that":[4,73],"inputs":[5],"and":[6,35,136,141,151,156,166,190],"pairwise":[7,126,175,211],"positive":[8],"relationships":[9],"are":[10,32],"enough":[11],"to":[12,37,42,59,80,98],"learn":[13],"meaningful":[14],"representations.":[15],"Although":[16],"SSL":[17,184],"has":[18],"recently":[19],"reached":[20],"a":[21,49],"milestone:":[22],"outperforming":[23],"supervised":[24,194],"methods":[25,83,153,160],"in":[26,114,197],"many":[27],"modalities\\dots":[28],"the":[29,53,64,101,109,115,122,125,145,164,174,180,193,198,210,216],"theoretical":[30,147],"foundations":[31],"limited,":[33],"method-specific,":[34],"fail":[36],"provide":[38],"principled":[39],"design":[40],"guidelines":[41],"practitioners.":[43],"In":[44],"this":[45,67],"paper,":[46],"we":[47,69],"propose":[48],"unifying":[50],"framework":[51],"under":[52],"helm":[54],"of":[55,66,124,133,168],"spectral":[56,82,158],"manifold":[57],"learning":[58],"address":[60],"those":[61,134],"limitations.":[62],"Through":[63],"course":[65],"study,":[68],"will":[70,94,191],"rigorously":[71],"demonstrate":[72],"VICReg,":[74],"SimCLR,":[75],"BarlowTwins":[76],"et":[77,90],"al.":[78,91],"correspond":[79],"eponymous":[81],"such":[84],"as":[85],"Laplacian":[86],"Eigenmaps,":[87],"Multidimensional":[88],"Scaling":[89],"This":[92],"unification":[93],"then":[95],"allow":[96],"us":[97],"obtain":[99],"(i)":[100,172],"closed-form":[102,110],"optimal":[103,111],"representation":[104],"for":[105,118],"each":[106,119,132],"method,":[107,120,195],"(ii)":[108,208],"network":[112],"parameters":[113],"linear":[116],"regime":[117],"(iii)":[121],"impact":[123],"relations":[127],"used":[128],"during":[129],"training":[130],"on":[131,137],"quantities":[135],"downstream":[138,181,217],"task":[139],"performances,":[140],"most":[142],"importantly,":[143],"(iv)":[144],"first":[146],"bridge":[148],"between":[149],"contrastive":[150],"non-contrastive":[152],"towards":[154],"global":[155],"local":[157],"embedding":[159],"respectively,":[161],"hinting":[162],"at":[163],"benefits":[165],"limitations":[167],"each.":[169],"For":[170],"example,":[171],"if":[173,209],"relation":[176,212],"is":[177,213],"aligned":[178],"with":[179,215,220],"task,":[182,218],"any":[183],"method":[185],"can":[186],"be":[187,206,225],"employed":[188],"successfully":[189],"recover":[192],"but":[196],"low":[199],"data":[200],"regime,":[201],"VICReg's":[202],"invariance":[203,222],"hyper-parameter":[204,223],"should":[205,224],"high;":[207],"misaligned":[214],"VICReg":[219],"small":[221],"preferred":[226],"over":[227],"SimCLR":[228],"or":[229],"BarlowTwins.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":18}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-03-03T00:00:00"}