{"id":"https://openalex.org/W7164522874","doi":"https://doi.org/10.1109/msp.2026.3659059","title":"Spectral Graph Theory: The mathematics of self-supervised learning [Special Issue on the Mathematics of Deep Learning]","display_name":"Spectral Graph Theory: The mathematics of self-supervised learning [Special Issue on the Mathematics of Deep Learning]","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7164522874","doi":"https://doi.org/10.1109/msp.2026.3659059"},"language":null,"primary_location":{"id":"doi:10.1109/msp.2026.3659059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2026.3659059","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047293370","display_name":"Randall Balestriero","orcid":"https://orcid.org/0000-0002-5692-4187"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Randall Balestriero","raw_affiliation_strings":["Brown University, Providence, RI, USA"],"raw_orcid":"https://orcid.org/0000-0002-5692-4187","affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113433465","display_name":"Yann Lecun","orcid":null},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yann LeCun","raw_affiliation_strings":["NYU Center for Data Science, Courant Institute of Mathematical Sciences, New York University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Center for Data Science, Courant Institute of Mathematical Sciences, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I36672615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94935961,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"43","issue":"3","first_page":"8","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.12950000166893005,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.12950000166893005,"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/T10320","display_name":"Neural Networks and Applications","score":0.048900000751018524,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.04439999908208847,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/graph","display_name":"Graph","score":0.49149999022483826},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3962000012397766},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.3684000074863434},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.3012999892234802},{"id":"https://openalex.org/keywords/spectral-analysis","display_name":"Spectral analysis","score":0.2827000021934509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5426999926567078},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37560001015663147},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3675000071525574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33250001072883606},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C2983668108","wikidata":"https://www.wikidata.org/wiki/Q280453","display_name":"Spectral analysis","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C74003402","wikidata":"https://www.wikidata.org/wiki/Q3180727","display_name":"Spectral graph theory","level":5,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msp.2026.3659059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2026.3659059","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1484040084","https://openalex.org/W1923807516","https://openalex.org/W1995341919","https://openalex.org/W2000769684","https://openalex.org/W2001771035","https://openalex.org/W2053395383","https://openalex.org/W2112796928","https://openalex.org/W2136150165","https://openalex.org/W2154136024","https://openalex.org/W2164291529","https://openalex.org/W2171590421","https://openalex.org/W2963446712","https://openalex.org/W3207924272","https://openalex.org/W4250837254","https://openalex.org/W4255949318","https://openalex.org/W4388979610","https://openalex.org/W4415796842","https://openalex.org/W7133239594","https://openalex.org/W7133259885"],"related_works":[],"abstract_inverted_index":{"Possessing":[0],"a":[1,8,60,87,95,118,144,156,160],"manipulable":[2],"representation":[3],"of":[4,36,109,122,174,196,204,231,243,261,273],"the":[5,19,34,148,168,188,194,197,220,229,239,252,259,262,271],"world":[6],"is":[7,33,101,234,267],"requirement":[9],"for":[10],"intelligent":[11],"machines":[12],"to":[13,53,72,103,154,211],"plan,":[14],"reason,":[15],"and":[16,69,74,83,97,105,130,151,181,241,254,265,281],"act":[17],"in":[18,184],"world.":[20],"Endowing":[21],"computational":[22],"systems,":[23],"e.g.,":[24],"deep":[25],"networks":[26],"(DNs),":[27],"with":[28,247,270],"artificial":[29],"intelligence":[30],"(AI)":[31],"capabilities":[32],"goal":[35],"self-supervised":[37],"learning":[38,153,215],"(SSL).":[39],"Immense":[40],"optimism,":[41],"fueled":[42],"by":[43,167,236],"early":[44,57],"successes,":[45],"funneled":[46],"vast":[47,172],"resources":[48],"into":[49],"SSL,":[50],"which":[51,99],"led":[52],"fast-paced":[54],"but":[55],"fragmented":[56],"developments.":[58],"As":[59,202],"result,":[61],"today\u2019s":[62],"SSL":[63,79,93,123,137,175,210,217],"research":[64,80],"has":[65],"become":[66],"costly,":[67],"slow-paced,":[68],"often":[70],"akin":[71],"trial":[73],"error.":[75],"To":[76,112],"ensure":[77],"that":[78,91,113,124,135,163,179,200],"remains":[81],"innovative":[82],"fail-proof,":[84],"we":[85,115,207],"present":[86],"unifying":[88],"mathematical":[89],"language":[90],"underpins":[92],"as":[94,141,165,277],"whole,":[96],"from":[98],"it":[100],"possible":[102,225],"explain":[104],"provably":[106],"alleviate":[107],"some":[108],"its":[110],"limitations.":[111],"end,":[114],"bring":[116],"forward":[117],"spectral":[119,131],"graph":[120,132,146],"theory":[121],"will":[125],"rely":[126],"on":[127,162,199,251],"harmonic":[128],"analysis":[129],"theory.":[133],"Under":[134],"view,":[136],"can":[138],"be":[139],"summarized":[140],"1)":[142],"estimating":[143],"relationship":[145],"between":[147],"dataset":[149],"samples":[150],"2)":[152],"produce":[155],"smooth":[157],"signal":[158],"(from":[159],"DN)":[161],"graph,":[164,189],"measured":[166],"Dirichlet":[169],"energy.":[170],"The":[171],"collection":[173],"methods":[176],"fall":[177],"under":[178],"formulation":[180,233],"differ":[182],"only":[183],"how":[185,191],"they":[186,192],"estimate":[187],"or":[190],"measure":[193],"energy":[195],"prediction":[198],"graph.":[201],"part":[203],"this":[205],"development,":[206],"also":[208],"ground":[209],"an":[212],"ideal":[213],"supervised":[214],"task:":[216],"objectives":[218],"minimize":[219],"expected":[221],"risk":[222],"over":[223],"all":[224],"downstream":[226],"tasks.":[227],"Finally,":[228],"practicality":[230],"our":[232],"showcased":[235],"precisely":[237],"pinpointing":[238],"benefits":[240],"pitfalls":[242],"each":[244],"method,":[245],"along":[246,269],"their":[248],"underlying":[249],"assumptions":[250],"data":[253,263,282],"system":[255],"design.":[256],"For":[257],"example,":[258],"impact":[260],"quality":[264],"sampling":[266],"studied,":[268],"role":[272],"various":[274],"hyperparameters":[275],"such":[276],"minibatch":[278],"size,":[279],"regularization,":[280],"augmentation.":[283]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2026-06-13T00:00:00"}