{"id":"https://openalex.org/W4387724787","doi":"https://doi.org/10.48550/arxiv.2310.10143","title":"An Empirical Study of Simplicial Representation Learning with Wasserstein Distance","display_name":"An Empirical Study of Simplicial Representation Learning with Wasserstein Distance","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387724787","doi":"https://doi.org/10.48550/arxiv.2310.10143"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2310.10143","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_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2310.10143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046358579","display_name":"Makoto Yamada","orcid":"https://orcid.org/0000-0001-7508-5094"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yamada, Makoto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046809463","display_name":"Yuki Takezawa","orcid":"https://orcid.org/0000-0002-8532-2775"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takezawa, Yuki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052544917","display_name":"Guillaume Houry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Houry, Guillaume","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093081379","display_name":"Kira Michaela Dusterwald","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dusterwald, Kira Michaela","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025723364","display_name":"D\u00e9borah Sulem","orcid":"https://orcid.org/0000-0003-4781-4848"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sulem, Deborah","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101575772","display_name":"Han Zhao","orcid":"https://orcid.org/0000-0003-1158-0779"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015826285","display_name":"Yao-Hung Hubert Tsai","orcid":"https://orcid.org/0000-0001-5312-1875"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsai, Yao-Hung Hubert","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"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":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":65},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9797,"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":0.9797,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9612,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9314,"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/softmax-function","display_name":"Softmax function","score":0.71212524},{"id":"https://openalex.org/keywords/earth-movers-distance","display_name":"Earth mover's distance","score":0.5410911},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization","score":0.49629146},{"id":"https://openalex.org/keywords/representation","display_name":"Representation","score":0.43079758}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.71212524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.66162807},{"id":"https://openalex.org/C82668687","wikidata":"https://www.wikidata.org/wiki/Q3046456","display_name":"Earth mover's distance","level":2,"score":0.5410911},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.49629146},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.48686925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43643367},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43079758},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3303984},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2113435},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2310.10143","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_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.10143","pdf_url":"http://arxiv.org/pdf/2310.10143","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2310.10143","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2310.10143","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_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4303493643","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W3108503355","https://openalex.org/W3107204728","https://openalex.org/W3090555870","https://openalex.org/W3022820045","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W2912971006"],"abstract_inverted_index":{"In":[0,36],"this":[1,69],"study,":[2],"we":[3,91,141,201],"delve":[4],"into":[5],"the":[6,13,29,39,58,62,77,80,93,109,112,148,159,173,178,183,192,204,208],"problem":[7],"of":[8,95,98,147,166,185,207],"self-supervised":[9],"learning":[10],"(SSL)":[11],"utilizing":[12,57],"1-Wasserstein":[14],"distance":[15,22,31,64,82],"on":[16,135,182],"a":[17,73,85,121,144,163],"tree":[18],"structure":[19],"(a.k.a.,":[20],"Tree-Wasserstein":[21],"(TWD)),":[23],"where":[24],"TWD":[25,99,152,167,186,209],"is":[26,42,65],"defined":[27],"as":[28,45],"L1":[30],"between":[32],"two":[33,96],"tree-embedded":[34],"vectors.":[35],"SSL":[37,78],"methods,":[38],"cosine":[40,214],"similarity":[41],"often":[43],"utilized":[44],"an":[46],"objective":[47],"function;":[48],"however,":[49],"it":[50],"has":[51],"not":[52],"been":[53],"well":[54],"studied":[55],"when":[56],"Wasserstein":[59,63,81],"distance.":[60],"Training":[61],"numerically":[66],"challenging.":[67],"Thus,":[68],"study":[70],"empirically":[71],"investigates":[72],"strategy":[74],"for":[75],"optimizing":[76],"with":[79],"and":[83,102,104,116,139,151,168,187,190,210],"finds":[84],"stable":[86],"training":[87],"procedure.":[88],"More":[89],"specifically,":[90],"evaluate":[92],"combination":[94,146,165,184,206],"types":[97],"(total":[100],"variation":[101],"ClusterTree)":[103],"several":[105],"probability":[106,114,188,211],"models,":[107],"including":[108],"softmax":[110,149],"function,":[111],"ArcFace":[113],"model,":[115,189],"simplicial":[117],"embedding.":[118],"We":[119,175],"propose":[120],"simple":[122,145,164],"yet":[123],"effective":[124],"Jeffrey":[125,193],"divergence-based":[126],"regularization":[127,195],"method":[128],"to":[129,171],"stabilize":[130],"optimization.":[131],"Through":[132],"empirical":[133],"experiments":[134],"STL10,":[136],"CIFAR10,":[137],"CIFAR100,":[138],"SVHN,":[140],"find":[142,176],"that":[143,177,191,203],"function":[150],"can":[153],"obtain":[154],"significantly":[155],"lower":[156],"results":[157],"than":[158],"standard":[160],"SimCLR.":[161],"Moreover,":[162],"SimSiam":[169],"fails":[170],"train":[172],"model.":[174],"model":[179,198,212],"performance":[180],"depends":[181],"divergence":[194],"helps":[196],"in":[197],"training.":[199],"Finally,":[200],"show":[202],"appropriate":[205],"outperforms":[213],"similarity-based":[215],"representation":[216],"learning.":[217]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4387724787","counts_by_year":[],"updated_date":"2025-04-11T23:42:39.621015","created_date":"2023-10-18"}