{"id":"https://openalex.org/W2992469714","doi":null,"title":"Large scale representation learning from triplet comparisons","display_name":"Large scale representation learning from triplet comparisons","publication_year":2019,"publication_date":"2019-09-25","ids":{"openalex":"https://openalex.org/W2992469714","mag":"2992469714"},"language":"en","primary_location":{"id":"mag:2992469714","doi":null,"is_oa":true,"landing_page_url":"https://openreview.net/pdf?id=rklhqkHFDB","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://openreview.net/pdf?id=rklhqkHFDB","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004296852","display_name":"Siavash Haghiri","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siavash Haghiri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064168352","display_name":"Leena Chennuru Vankadara","orcid":"https://orcid.org/0000-0002-3810-840X","observed_orcids":["https://orcid.org/0000-0002-3810-840X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leena Chennuru Vankadara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083754306","display_name":"Ulrike Von Luxburg A","orcid":"https://orcid.org/0009-0001-9902-2220","observed_orcids":["https://orcid.org/0009-0001-9902-2220"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ulrike von Luxburg","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":2,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.20499999821186066,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.20499999821186066,"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":0.1898999959230423,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.09489999711513519,"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/representation-learning","display_name":"representation learning","score":0.8679999709129333},{"id":"https://openalex.org/keywords/ordinal-embedding","display_name":"ordinal embedding","score":0.9700000286102295},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.38100001215934753},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.8059999942779541},{"id":"https://openalex.org/keywords/large-scale-datasets","display_name":"large-scale datasets","score":0.6729999780654907},{"id":"https://openalex.org/keywords/nonconvex-optimization","display_name":"non-convex optimization","score":0.7990000247955322},{"id":"https://openalex.org/keywords/np-hard-optimization-problems","display_name":"NP-hard optimization","score":0.7850000262260437},{"id":"https://openalex.org/keywords/similarity-learning","display_name":"similarity learning","score":0.3059999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015990614891052},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6835542321205139},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6659407019615173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6178547143936157},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5990520715713501},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5857748985290527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5705491304397583},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.56849604845047},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5018374919891357},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45034971833229065},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.420674204826355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3307086229324341},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":1,"locations":[{"id":"mag:2992469714","doi":null,"is_oa":true,"landing_page_url":"https://openreview.net/pdf?id=rklhqkHFDB","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2992469714","doi":null,"is_oa":true,"landing_page_url":"https://openreview.net/pdf?id=rklhqkHFDB","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W68180256","https://openalex.org/W85455704","https://openalex.org/W219040644","https://openalex.org/W639708223","https://openalex.org/W1450455737","https://openalex.org/W1522301498","https://openalex.org/W1839408879","https://openalex.org/W1859119539","https://openalex.org/W1903029394","https://openalex.org/W1946606198","https://openalex.org/W1968265719","https://openalex.org/W1973192023","https://openalex.org/W2021354639","https://openalex.org/W2031494345","https://openalex.org/W2043005456","https://openalex.org/W2088247287","https://openalex.org/W2096733369","https://openalex.org/W2100659887","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2108665656","https://openalex.org/W2110798204","https://openalex.org/W2111239341","https://openalex.org/W2112935422","https://openalex.org/W2118393783","https://openalex.org/W2162724919","https://openalex.org/W2166116275","https://openalex.org/W2173520492","https://openalex.org/W2175852750","https://openalex.org/W2187089797","https://openalex.org/W2413665233","https://openalex.org/W2569300915","https://openalex.org/W2607412481","https://openalex.org/W2608609325","https://openalex.org/W2750384547","https://openalex.org/W2786464815","https://openalex.org/W2797492201","https://openalex.org/W2895347732","https://openalex.org/W2917551568","https://openalex.org/W2946375767","https://openalex.org/W2950133940","https://openalex.org/W2950220847","https://openalex.org/W2963485174","https://openalex.org/W2963488971","https://openalex.org/W2969775752","https://openalex.org/W3044521504"],"related_works":["https://openalex.org/W1839408879","https://openalex.org/W6941460483","https://openalex.org/W2907378409","https://openalex.org/W2921849081","https://openalex.org/W4246940132","https://openalex.org/W4390589804","https://openalex.org/W7221410301","https://openalex.org/W6889207973","https://openalex.org/W7164884344","https://openalex.org/W6885151657"],"abstract_inverted_index":{"In":[0,74],"this":[1],"paper,":[2],"we":[3,78,90,190],"discuss":[4],"the":[5,24,28,40,71,75,85,94,101,129,133,136,152,159,195],"fundamental":[6],"problem":[7,141,160],"of":[8,27,68,84,100,148,199],"representation":[9,34,61,83,127],"learning":[10,150,216],"from":[11],"a":[12,47,58,117,125,146],"new":[13],"perspective.":[14],"It":[15],"has":[16,42,142],"been":[17,43,143],"observed":[18],"in":[19,53,70,145,214],"many":[20,36],"supervised/unsupervised":[21],"DNNs":[22,122],"that":[23,80,123,172,211],"final":[25],"layer":[26],"network":[29,41],"often":[30],"provides":[31],"an":[32],"informative":[33],"for":[35,62,64,128],"tasks,":[37],"even":[38],"though":[39],"trained":[44],"to":[45,96,109,135,158,167,185,194,203],"perform":[46],"particular":[48],"task.":[49],"The":[50],"common":[51],"ingredient":[52],"all":[54],"previous":[55],"studies":[56],"is":[57,87,176],"low-level":[59],"feature":[60],"items,":[63,130],"example,":[65],"RGB":[66],"values":[67],"images":[69],"image":[72],"context.":[73],"present":[76],"work,":[77],"assume":[79],"no":[81],"meaningful":[82],"items":[86],"given.":[88],"Instead,":[89],"are":[91,161],"provided":[92],"with":[93],"answers":[95,134],"some":[97],"triplet":[98,138],"comparisons":[99],"following":[102],"form:":[103],"Is":[104],"item":[105,110,113],"A":[106],"more":[107],"similar":[108],"B":[111],"or":[112],"C?":[114],"We":[115,170],"provide":[116],"fast":[118],"algorithm":[119],"based":[120],"on":[121],"constructs":[124],"Euclidean":[126],"using":[131,200],"solely":[132],"above-mentioned":[137],"comparisons.":[139],"This":[140],"studied":[144],"sub-community":[147],"machine":[149],"by":[151],"name":[153],"Ordinal":[154],"Embedding.":[155],"Previous":[156],"approaches":[157],"painfully":[162],"slow":[163],"and":[164,182],"cannot":[165],"scale":[166,184],"larger":[168],"datasets.":[169,188],"demonstrate":[171],"our":[173],"proposed":[174],"approach":[175],"significantly":[177],"faster":[178],"than":[179],"available":[180],"methods,":[181],"can":[183],"real-world":[186],"large":[187],"\r\nThereby,":[189],"also":[191],"draw":[192],"attention":[193],"less":[196],"explored":[197],"idea":[198],"neural":[201],"networks":[202],"directly,":[204],"approximately":[205],"solve":[206],"non-convex,":[207],"NP-hard":[208],"optimization":[209],"problems":[210],"arise":[212],"naturally":[213],"unsupervised":[215],"problems.":[217]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-12-13T00:00:00"}