{"id":"https://openalex.org/W4385568070","doi":"https://doi.org/10.1145/3580305.3599263","title":"BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs","display_name":"BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385568070","doi":"https://doi.org/10.1145/3580305.3599263"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599263","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599263","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599263","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008170956","display_name":"Zhen Yang","orcid":"https://orcid.org/0000-0002-1346-7430"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1346-7430","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101942668","display_name":"Tinglin Huang","orcid":"https://orcid.org/0009-0005-5644-4879"},"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":"Tinglin Huang","raw_affiliation_strings":["Yale University & Yale University, New Haven, CT, USA"],"raw_orcid":"https://orcid.org/0009-0005-5644-4879","affiliations":[{"raw_affiliation_string":"Yale University & Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075227380","display_name":"Ding Ming","orcid":"https://orcid.org/0000-0001-5152-7011"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Ding","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5152-7011","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052284218","display_name":"Yuxiao Dong","orcid":"https://orcid.org/0000-0002-6092-2002"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiao Dong","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6092-2002","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078337825","display_name":"Rex Ying","orcid":"https://orcid.org/0000-0002-5856-5229"},"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":"Rex Ying","raw_affiliation_strings":["Yale University, New Haven, CT, USA"],"raw_orcid":"https://orcid.org/0000-0002-5856-5229","affiliations":[{"raw_affiliation_string":"Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035985651","display_name":"Yukuo Cen","orcid":"https://orcid.org/0000-0001-5682-2810"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukuo Cen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5682-2810","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018191388","display_name":"Yangli\u2010ao Geng","orcid":"https://orcid.org/0000-0003-0173-4041"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangliao Geng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0173-4041","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044791875","display_name":"Jie Tang","orcid":"https://orcid.org/0000-0003-3487-4593"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Tang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3487-4593","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5008170956"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.2153,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90172748,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3057","last_page":"3069"},"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":0.9993000030517578,"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":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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":0.9937000274658203,"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":0.792305588722229},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6732720136642456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5740464329719543},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5295418500900269},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5115469694137573},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.42982667684555054},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.41305607557296753},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3566740155220032},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3289019465446472},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.28115883469581604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.792305588722229},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6732720136642456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5740464329719543},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5295418500900269},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5115469694137573},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.42982667684555054},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41305607557296753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3566740155220032},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3289019465446472},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28115883469581604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599263","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599263","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3580305.3599263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599263","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599263","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5614798656","display_name":null,"funder_award_id":"61825602","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6048029205","display_name":null,"funder_award_id":"62276148","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385568070.pdf","grobid_xml":"https://content.openalex.org/works/W4385568070.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2008857988","https://openalex.org/W2086254934","https://openalex.org/W2096188852","https://openalex.org/W2102035799","https://openalex.org/W2115741288","https://openalex.org/W2126400076","https://openalex.org/W2133299088","https://openalex.org/W2133458109","https://openalex.org/W2142498761","https://openalex.org/W2194775991","https://openalex.org/W2752289368","https://openalex.org/W2798991696","https://openalex.org/W2962756421","https://openalex.org/W2998702515","https://openalex.org/W3035524453","https://openalex.org/W3036320503","https://openalex.org/W3036446966","https://openalex.org/W3080456792","https://openalex.org/W3095746859","https://openalex.org/W3098468692","https://openalex.org/W3099152386","https://openalex.org/W3099700870","https://openalex.org/W3106743555","https://openalex.org/W3114632476","https://openalex.org/W3145450063","https://openalex.org/W3154503084","https://openalex.org/W3154677174","https://openalex.org/W3156636935","https://openalex.org/W3172854437","https://openalex.org/W3201301914","https://openalex.org/W3213582899","https://openalex.org/W4210896998","https://openalex.org/W4214481550","https://openalex.org/W4290874851","https://openalex.org/W6681029592"],"related_works":["https://openalex.org/W2787993192","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W3033859939","https://openalex.org/W2847365777","https://openalex.org/W3128025644","https://openalex.org/W2355048207","https://openalex.org/W1185300216","https://openalex.org/W3126051647","https://openalex.org/W2042102171"],"abstract_inverted_index":{"In-Batch":[0],"contrastive":[1,73,153,178],"learning":[2,74,154],"is":[3,25,60,86,140],"a":[4,19,36,141],"state-of-the-art":[5],"self-supervised":[6],"method":[7],"that":[8,146,169],"brings":[9],"semantically-similar":[10],"instances":[11,16],"close":[12],"while":[13],"pushing":[14],"dissimilar":[15],"apart":[17],"within":[18,41,54],"mini-batch.":[20,43],"Its":[21],"key":[22],"to":[23,47,71,90,100,134],"success":[24],"the":[26,39,42,55,63,79,114,122,131,174],"negative":[27,37],"sharing":[28],"strategy,":[29],"in":[30,156],"which":[31],"every":[32],"instance":[33],"serves":[34],"as":[35,180],"for":[38],"others":[40],"Recent":[44],"studies":[45],"aim":[46],"improve":[48,72,173],"performance":[49,175],"by":[50,62,75,182],"sampling":[51,76],"hard":[52,96],"negatives":[53,99],"current":[56],"mini-batch,":[57,123],"whose":[58],"quality":[59],"bounded":[61],"mini-batch":[64,107],"itself.":[65],"In":[66],"this":[67],"work,":[68],"we":[69,112,124],"propose":[70],"mini-batches":[77,92],"from":[78],"input":[80],"data.":[81],"We":[82],"present":[83],"BatchSampler\\footnoteThe":[84],"code":[85],"available":[87],"at":[88],"BatchSampler":[89,139,170],"sample":[91,136],"of":[93,117,165,176,185],"hard-to-distinguish":[94,137],"(i.e.,":[95],"and":[97,143,159,193,195],"true":[98],"each":[101,106],"other)":[102],"instances.":[103,119,138],"To":[104,120],"make":[105],"have":[108],"fewer":[109],"false":[110],"negatives,":[111],"design":[113],"proximity":[115,132],"graph":[116,133,198],"randomly-selected":[118],"form":[121],"leverage":[125],"random":[126],"walk":[127],"with":[128],"restart":[129],"on":[130,163,187,190,197],"help":[135],"simple":[142],"general":[144],"technique":[145],"can":[147,171],"be":[148],"directly":[149],"plugged":[150],"into":[151],"existing":[152],"models":[155],"vision,":[157],"language,":[158],"graphs.":[160],"Extensive":[161],"experiments":[162],"datasets":[164],"three":[166],"modalities":[167],"show":[168],"consistently":[172],"powerful":[177],"models,":[179],"shown":[181],"significant":[183],"improvements":[184],"SimCLR":[186],"ImageNet-100,":[188],"SimCSE":[189],"STS":[191],"(language),":[192],"GraphCL":[194],"MVGRL":[196],"datasets.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}