{"id":"https://openalex.org/W3166426964","doi":"https://doi.org/10.1145/3447548.3467241","title":"Triplet Attention","display_name":"Triplet Attention","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3166426964","doi":"https://doi.org/10.1145/3447548.3467241","mag":"3166426964"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & 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/A5086419494","display_name":"Haoyi Zhou","orcid":"https://orcid.org/0000-0002-2393-3634"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyi Zhou","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380463","display_name":"Jianxin Li","orcid":"https://orcid.org/0000-0001-5152-0055"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051856627","display_name":"Jieqi Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieqi Peng","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328838","display_name":"Shuai Zhang","orcid":"https://orcid.org/0000-0001-8502-2927"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["Beihang University, Beijing, China","University of California, Berkeley, California, CA, USA"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"University of California, Berkeley, California, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013030532","display_name":"Shanghang Zhang","orcid":"https://orcid.org/0000-0003-4047-3526"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Shanghang Zhang","raw_affiliation_strings":["Beihang University, Beijing, China","University of California, Berkeley, California, CA, USA"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"University of California, Berkeley, California, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086419494"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.77663056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2378","last_page":"2388"},"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":0.9886000156402588,"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":0.9886000156402588,"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/T10028","display_name":"Topic Modeling","score":0.9746999740600586,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9714999794960022,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7486521005630493},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6915386319160461},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5978289246559143},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.48089078068733215},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4478491544723511},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.43077465891838074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3889588713645935},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3735126852989197},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1360255479812622},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09793642163276672},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0787370502948761}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486521005630493},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6915386319160461},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5978289246559143},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.48089078068733215},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4478491544723511},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.43077465891838074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3889588713645935},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3735126852989197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1360255479812622},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09793642163276672},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0787370502948761},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447548.3467241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G649362005","display_name":null,"funder_award_id":"SKLSDE-2020ZX-12","funder_id":"https://openalex.org/F4320326978","funder_display_name":"State Key Laboratory of Software Development Environment"}],"funders":[{"id":"https://openalex.org/F4320326978","display_name":"State Key Laboratory of Software Development Environment","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2046468368","https://openalex.org/W2049387919","https://openalex.org/W2067906953","https://openalex.org/W2144902422","https://openalex.org/W2626778328","https://openalex.org/W2739537633","https://openalex.org/W2740785367","https://openalex.org/W2799054028","https://openalex.org/W2896457183","https://openalex.org/W2950739196","https://openalex.org/W2950784811","https://openalex.org/W2962690139","https://openalex.org/W2962822108","https://openalex.org/W2963488971","https://openalex.org/W2963744496","https://openalex.org/W2963748441","https://openalex.org/W2972324944","https://openalex.org/W2978017171","https://openalex.org/W2979826702","https://openalex.org/W2995575179","https://openalex.org/W3000514857","https://openalex.org/W3001434439","https://openalex.org/W3085139254","https://openalex.org/W3107826490","https://openalex.org/W3119866685","https://openalex.org/W3121523901","https://openalex.org/W3177318507"],"related_works":["https://openalex.org/W2067317451","https://openalex.org/W2154771632","https://openalex.org/W4211085505","https://openalex.org/W3122478268","https://openalex.org/W2084758217","https://openalex.org/W408804804","https://openalex.org/W4231021675","https://openalex.org/W3086365953","https://openalex.org/W4226072953","https://openalex.org/W2392606101"],"abstract_inverted_index":{"The":[0,116],"Transformer":[1],"model":[2],"has":[3],"benefited":[4],"various":[5,141],"real-world":[6],"applications,":[7],"where":[8],"the":[9,23,35,42,47,58,64,69,79,83,88,103,124],"self-attention":[10,26,89],"mechanism":[11,90],"with":[12,78],"dot-products":[13],"shows":[14],"superior":[15],"alignment":[16],"ability":[17],"on":[18,31,68,140],"building":[19],"long":[20],"dependency.":[21,60,99],"However,":[22],"pair-wisely":[24],"attended":[25],"limits":[27],"further":[28],"performance":[29,138],"improvement":[30,139],"challenging":[32],"tasks.":[33],"To":[34],"extent":[36],"of":[37],"our":[38,134],"knowledge,":[39],"this":[40],"is":[41],"first":[43],"work":[44],"to":[45,91,93,109,114],"define":[46,63],"Triplet":[48],"Attention":[49],"(A3)":[50],"for":[51],"Transformer,":[52],"which":[53,73],"introduces":[54],"triplet":[55,65,71],"connections":[56],"as":[57],"complementary":[59],"Specifically,":[61],"we":[62,101],"attention":[66],"based":[67],"scalar":[70],"product,":[72],"may":[74],"be":[75,120],"interchangeably":[76],"used":[77],"canonical":[80],"one":[81],"within":[82],"multi-head":[84],"attention.":[85],"It":[86],"allows":[87],"attend":[92],"diverse":[94],"triplets":[95],"and":[96,106,143],"capture":[97],"complex":[98],"Then,":[100],"utilize":[102],"permuted":[104],"formulation":[105],"kernel":[107],"tricks":[108],"establish":[110],"a":[111],"linear":[112],"approximation":[113],"A3.":[115],"proposed":[117],"architecture":[118],"could":[119],"smoothly":[121],"integrated":[122],"into":[123],"pre-training":[125],"by":[126],"modifying":[127],"head":[128],"configurations.":[129],"Extensive":[130],"experiments":[131],"show":[132],"that":[133],"methods":[135],"achieve":[136],"significant":[137],"tasks":[142],"two":[144],"benchmarks.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-06-22T00:00:00"}