{"id":"https://openalex.org/W4286748649","doi":"https://doi.org/10.1145/3534678.3539311","title":"Contrastive Learning with Complex Heterogeneity","display_name":"Contrastive Learning with Complex Heterogeneity","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4286748649","doi":"https://doi.org/10.1145/3534678.3539311"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539311","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539311","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5018530326","display_name":"Lecheng Zheng","orcid":"https://orcid.org/0000-0002-6869-3320"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lecheng Zheng","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030156276","display_name":"Jinjun Xiong","orcid":"https://orcid.org/0000-0002-2620-4859"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinjun Xiong","raw_affiliation_strings":["University at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057639889","display_name":"Yan Zhu","orcid":"https://orcid.org/0000-0002-5952-2108"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yada Zhu","raw_affiliation_strings":["MIT-IBM Watson AI Lab, IBM Research, Boston, NY, USA"],"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab, IBM Research, Boston, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073158087","display_name":"Jingrui He","orcid":"https://orcid.org/0000-0002-6429-6272"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingrui He","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018530326"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06110228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2594","last_page":"2604"},"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":0.4090000092983246,"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":0.4090000092983246,"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":0.13510000705718994,"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":0.1031000018119812,"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/computer-science","display_name":"Computer science","score":0.7368651628494263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5999917387962341},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5388792157173157},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5288760662078857},{"id":"https://openalex.org/keywords/information-loss","display_name":"Information loss","score":0.4364597201347351},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.42365315556526184},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35928404331207275},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20854294300079346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368651628494263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5999917387962341},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5388792157173157},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5288760662078857},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.4364597201347351},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.42365315556526184},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35928404331207275},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20854294300079346}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539311","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539311","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8228424633","display_name":null,"funder_award_id":"IIS-1947203, IIS-2117902, IIS-2137468","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1937059634","https://openalex.org/W1990519701","https://openalex.org/W2008989859","https://openalex.org/W2035299679","https://openalex.org/W2037603696","https://openalex.org/W2048679005","https://openalex.org/W2098711149","https://openalex.org/W2112796928","https://openalex.org/W2129026672","https://openalex.org/W2156935079","https://openalex.org/W2238162249","https://openalex.org/W2359108789","https://openalex.org/W2549401308","https://openalex.org/W2605997098","https://openalex.org/W2758611985","https://openalex.org/W2972250269","https://openalex.org/W3093766087","https://openalex.org/W3152602106","https://openalex.org/W3166235106"],"related_works":["https://openalex.org/W11462192","https://openalex.org/W14516383","https://openalex.org/W6680660","https://openalex.org/W11830398","https://openalex.org/W9952751","https://openalex.org/W1243554","https://openalex.org/W14465466","https://openalex.org/W3979659","https://openalex.org/W5052411","https://openalex.org/W13661906"],"abstract_inverted_index":{"With":[0],"the":[1,14,36,50,98,114,119,134,140,159,167,171,177,184,188,191,205,208,211],"advent":[2],"of":[3,16,25,38,41,100,149,173,190,210,217],"big":[4],"data":[5,22,202],"across":[6],"multiple":[7,26,32,39,147,215],"high-impact":[8],"applications,":[9],"we":[10,124],"are":[11,29,46],"often":[12],"facing":[13],"challenge":[15],"complex":[17,51],"heterogeneity.":[18,42,150,218],"The":[19],"newly":[20],"collected":[21],"usually":[23],"consist":[24],"modalities":[27],"and":[28,139,207],"characterized":[30],"with":[31,53],"labels,":[33],"thus":[34],"exhibiting":[35],"co-existence":[37],"types":[40,148,216],"Although":[43],"state-of-the-art":[44],"techniques":[45],"good":[47],"at":[48],"modeling":[49,214],"heterogeneity":[52],"sufficient":[54],"label":[55,58],"information,":[56],"such":[57],"information":[59],"can":[60],"be":[61],"quite":[62],"expensive":[63],"to":[64,74,78,96,145,166,194],"obtain":[65],"in":[66,121,170],"real":[67],"applications.":[68],"Recently,":[69],"researchers":[70],"pay":[71],"great":[72],"attention":[73],"contrastive":[75,91,137,143,161],"learning":[76,92,129,162],"due":[77],"its":[79],"prominent":[80],"performance":[81],"by":[82],"utilizing":[83],"rich":[84],"unlabeled":[85],"data.":[86],"However,":[87],"existing":[88],"work":[89],"on":[90,187,200],"is":[93],"not":[94],"able":[95],"address":[97],"problem":[99],"false-negative":[101,174],"pairs,":[102,175],"i.e.,":[103],"some":[104],"'negative'":[105],"pairs":[106],"may":[107],"have":[108,113],"similar":[109],"representations":[110,193],"if":[111],"they":[112],"same":[115],"label.":[116],"To":[117],"overcome":[118],"issues,":[120],"this":[122,196],"paper,":[123],"propose":[125],"a":[126,154],"unified":[127],"heterogeneous":[128],"framework,":[130],"which":[131],"combines":[132],"both":[133],"weighted":[135,141,179],"unsupervised":[136],"loss":[138,144,163,180],"supervised":[142],"model":[146],"We":[151],"first":[152],"provide":[153],"theoretical":[155],"analysis":[156],"showing":[157],"that":[158],"vanilla":[160],"easily":[164],"leads":[165],"sub-optimal":[168],"solution":[169],"presence":[172],"whereas":[176],"proposed":[178,212],"could":[181],"automatically":[182],"adjust":[183],"weight":[185],"based":[186],"similarity":[189],"learned":[192],"mitigate":[195],"issue.":[197],"Experimental":[198],"results":[199],"real-world":[201],"sets":[203],"demonstrate":[204],"effectiveness":[206],"efficiency":[209],"framework":[213]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2022-07-23T00:00:00"}