{"id":"https://openalex.org/W4393406722","doi":"https://doi.org/10.1109/ciss59072.2024.10480166","title":"Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy","display_name":"Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy","publication_year":2024,"publication_date":"2024-03-13","ids":{"openalex":"https://openalex.org/W4393406722","doi":"https://doi.org/10.1109/ciss59072.2024.10480166"},"language":"en","primary_location":{"id":"doi:10.1109/ciss59072.2024.10480166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss59072.2024.10480166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-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/A5011524766","display_name":"Danqi Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Danqi Liao","raw_affiliation_strings":["Yale University"],"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100322216","display_name":"Chen Liu","orcid":"https://orcid.org/0009-0003-0430-6146"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Liu","raw_affiliation_strings":["Yale University"],"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102638392","display_name":"Benjamin W. Christensen","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin W. Christensen","raw_affiliation_strings":["Yale University"],"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053568123","display_name":"Alexander Tong","orcid":"https://orcid.org/0000-0002-2031-4096"},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Alexander Tong","raw_affiliation_strings":["Mila; Université de Montréal"],"affiliations":[{"raw_affiliation_string":"Mila; Université de Montréal","institution_ids":["https://openalex.org/I4210155582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034224130","display_name":"Guillaume Huguet","orcid":"https://orcid.org/0000-0002-4746-6030"},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Guillaume Huguet","raw_affiliation_strings":["Mila; Université de Montréal"],"affiliations":[{"raw_affiliation_string":"Mila; Université de Montréal","institution_ids":["https://openalex.org/I4210155582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005117825","display_name":"Guy Wolf","orcid":"https://orcid.org/0000-0002-6740-059X"},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Guy Wolf","raw_affiliation_strings":["Mila; Université de Montréal"],"affiliations":[{"raw_affiliation_string":"Mila; Université de Montréal","institution_ids":["https://openalex.org/I4210155582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000667901","display_name":"Maximilian Nickel","orcid":"https://orcid.org/0000-0001-5006-0827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maximilian Nickel","raw_affiliation_strings":["Meta AI (FAIR)"],"affiliations":[{"raw_affiliation_string":"Meta AI (FAIR)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014762708","display_name":"Ian Adelstein","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Adelstein","raw_affiliation_strings":["Yale University"],"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045475274","display_name":"Smita Krishnaswamy","orcid":"https://orcid.org/0000-0001-5823-1985"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Smita Krishnaswamy","raw_affiliation_strings":["Yale University","Meta AI (FAIR)"],"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]},{"raw_affiliation_string":"Meta AI (FAIR)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5011524766"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":1.0878,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79476754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9451000094413757,"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/T10320","display_name":"Neural Networks and Applications","score":0.9451000094413757,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.661442756652832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6481899619102478},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5341825485229492},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.522639274597168},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48530763387680054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46005862951278687},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4164283275604248},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4013770818710327},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3885405659675598},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09169536828994751}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.661442756652832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6481899619102478},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5341825485229492},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.522639274597168},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48530763387680054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46005862951278687},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4164283275604248},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4013770818710327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3885405659675598},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09169536828994751},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ciss59072.2024.10480166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss59072.2024.10480166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W632665696","https://openalex.org/W2040704490","https://openalex.org/W2080722576","https://openalex.org/W2092939357","https://openalex.org/W2114771311","https://openalex.org/W2127234432","https://openalex.org/W2134478553","https://openalex.org/W2150871663","https://openalex.org/W2187089797","https://openalex.org/W2496278891","https://openalex.org/W2610423314","https://openalex.org/W2622719862","https://openalex.org/W2805619986","https://openalex.org/W2912284931","https://openalex.org/W2963598015","https://openalex.org/W2963693826","https://openalex.org/W2964184826","https://openalex.org/W2993894543","https://openalex.org/W2996320484","https://openalex.org/W3106022083","https://openalex.org/W3153269443","https://openalex.org/W4213367101","https://openalex.org/W4376122984","https://openalex.org/W4378070712","https://openalex.org/W4389599417","https://openalex.org/W6680000691","https://openalex.org/W6680940449","https://openalex.org/W6752051073","https://openalex.org/W6758540577","https://openalex.org/W6774314701","https://openalex.org/W6852384002","https://openalex.org/W6859532474","https://openalex.org/W6888838614"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Entropy":[0],"and":[1,28,40,59,102,116,180,197],"mutual":[2,83,117],"information":[3,9,84,118],"in":[4,22,26,33,72,105,129],"neural":[5,73,119,144],"networks":[6,131],"provide":[7],"rich":[8],"on":[10,173,178,211],"the":[11,56,125,152,167],"learning":[12,158],"process,":[13],"but":[14,159],"they":[15,95],"have":[16],"proven":[17],"difficult":[18],"to":[19,44,54,192,203],"compute":[20,61],"reliably":[21,60],"high":[23],"dimensions.":[24],"Indeed,":[25],"noisy":[27],"high-dimensional":[29,106],"data,":[30],"traditional":[31],"estimates":[32],"ambient":[34],"dimensions":[35],"approach":[36],"a":[37,76],"fixed":[38],"entropy":[39,70],"are":[41],"prohibitively":[42],"hard":[43],"compute.":[45],"To":[46],"address":[47],"these":[48,62],"issues,":[49],"we":[50,66,92,185],"leverage":[51],"data":[52,108],"geometry":[53],"access":[55],"underlying":[57],"manifold":[58],"information-theoretic":[63],"measures.":[64],"Specifically,":[65],"define":[67],"diffusion":[68,81],"spectral":[69,82],"(DSE)":[71],"representations":[74,128,145],"of":[75,99,127,143],"dataset":[77],"as":[78,80],"well":[79],"(DSMI)":[85],"between":[86],"different":[87],"variables":[88],"representing":[89],"data.":[90],"First,":[91],"show":[93,186],"that":[94,109,140,187,198],"form":[96],"noise-resistant":[97],"measures":[98],"intrinsic":[100],"dimensionality":[101],"relationship":[103],"strength":[104],"simulated":[107],"outperform":[110],"classic":[111],"Shannon":[112],"entropy,":[113],"nonparametric":[114],"estimation,":[115],"estimation":[120],"(MINE).":[121],"We":[122,138],"then":[123],"study":[124],"evolution":[126],"classification":[130,206],"with":[132,151,166],"supervised":[133],"learning,":[134],"self-supervision,":[135],"or":[136],"overfitting.":[137],"observe":[139],"(1)":[141],"DSE":[142,188],"increases":[146,155],"during":[147,156,162],"training;":[148],"(2)":[149],"DSMI":[150,165,199],"class":[153],"label":[154],"generalizable":[157],"stays":[160],"stagnant":[161],"overfitting;":[163],"(3)":[164],"input":[168],"signal":[169],"shows":[170],"differing":[171],"trends:":[172],"MNIST":[174],"it":[175,182],"increases,":[176],"while":[177],"CIFAR-10":[179],"STL-10":[181],"decreases.":[183],"Finally,":[184],"can":[189,200],"be":[190,201],"used":[191,202],"guide":[193],"better":[194],"network":[195],"initialization":[196],"predict":[204],"downstream":[205],"accuracy":[207],"across":[208],"962":[209],"models":[210],"ImageNet.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}