{"id":"https://openalex.org/W3208451974","doi":"https://doi.org/10.1145/3459637.3482389","title":"Self-supervised Representation Learning on Dynamic Graphs","display_name":"Self-supervised Representation Learning on Dynamic Graphs","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3208451974","doi":"https://doi.org/10.1145/3459637.3482389","mag":"3208451974"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482389","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","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/A5102970944","display_name":"Sheng Tian","orcid":"https://orcid.org/0000-0003-3756-5454"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sheng Tian","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076272801","display_name":"Ruofan Wu","orcid":"https://orcid.org/0000-0001-6826-8108"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruofan Wu","raw_affiliation_strings":["Ant Group, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027999064","display_name":"Leilei Shi","orcid":"https://orcid.org/0000-0003-1953-6932"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leilei Shi","raw_affiliation_strings":["Ant Group, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029727411","display_name":"Zhu Liang","orcid":"https://orcid.org/0000-0001-6811-5451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Zhu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101439585","display_name":"Tao Xiong","orcid":"https://orcid.org/0000-0003-1583-8669"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Xiong","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102970944"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8073,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.94469302,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1814","last_page":"1823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9997000098228455,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9997000098228455,"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/T10269","display_name":"Epigenetics and DNA Methylation","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9383000135421753,"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":0.8172005414962769},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6165210604667664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5882925987243652},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5771074295043945},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5536379814147949},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5492720603942871},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45012688636779785},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43657371401786804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172005414962769},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6165210604667664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5882925987243652},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5771074295043945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5536379814147949},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5492720603942871},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45012688636779785},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43657371401786804},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3482389","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W1996816151","https://openalex.org/W2111708605","https://openalex.org/W2138621090","https://openalex.org/W2144902422","https://openalex.org/W2153972927","https://openalex.org/W2164067128","https://openalex.org/W2466501638","https://openalex.org/W2468907370","https://openalex.org/W2521218765","https://openalex.org/W2554952599","https://openalex.org/W2569283211","https://openalex.org/W2620820275","https://openalex.org/W2624431344","https://openalex.org/W2755092149","https://openalex.org/W2786464815","https://openalex.org/W2798991696","https://openalex.org/W2893944917","https://openalex.org/W2907192581","https://openalex.org/W2917551568","https://openalex.org/W2951585248","https://openalex.org/W2952254971","https://openalex.org/W2962711740","https://openalex.org/W2962756421","https://openalex.org/W2963460103","https://openalex.org/W2965556524","https://openalex.org/W2965683718","https://openalex.org/W2991079997","https://openalex.org/W2998116985","https://openalex.org/W2998269939","https://openalex.org/W2998313947","https://openalex.org/W3005680577","https://openalex.org/W3026076535","https://openalex.org/W3034693603","https://openalex.org/W3035065454","https://openalex.org/W3035524453","https://openalex.org/W3045255111","https://openalex.org/W3081963674","https://openalex.org/W3101588560","https://openalex.org/W3102419180","https://openalex.org/W3122137342","https://openalex.org/W3173151551","https://openalex.org/W4293651439","https://openalex.org/W4322614756","https://openalex.org/W6730084236","https://openalex.org/W6776137863"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W3048601286","https://openalex.org/W2965925734","https://openalex.org/W4386136067","https://openalex.org/W4286858940"],"abstract_inverted_index":{"Graph":[0],"representation":[1,30,92],"learning":[2,20,31,87,93,104,142],"has":[3,70],"now":[4],"become":[5],"the":[6,42,89,102,116,141,148,166,191,222],"de":[7],"facto":[8],"standard":[9],"when":[10],"dealing":[11],"with":[12,120,212],"graph-structured":[13],"data.":[14],"Using":[15],"powerful":[16],"tools":[17],"from":[18],"deep":[19],"and":[21,36,69,175,177],"graph":[22,29,45,85,210],"neural":[23],"networks,":[24],"recent":[25,127],"works":[26],"have":[27],"applied":[28],"to":[32,50,56,106,146,202],"time-evolving":[33],"dynamic":[34,44,84,96,107,209],"graphs":[35,108],"showed":[37],"promising":[38],"results.":[39],"However,":[40],"all":[41],"previous":[43],"models":[46,211],"require":[47],"labeled":[48],"samples":[49],"train,":[51],"which":[52],"might":[53],"be":[54],"costly":[55],"acquire":[57],"in":[58,74,144,152],"practice.":[59],"Self-supervision":[60],"offers":[61,225],"a":[62,121,134,186],"principled":[63],"way":[64],"of":[65,115,193],"utilizing":[66],"unlabeled":[67],"data":[68],"achieved":[71],"great":[72],"success":[73],"computer":[75],"vision":[76],"community.":[77],"In":[78],"this":[79],"paper":[80],"we":[81,132],"propose":[82,133],"debiased":[83,136],"contrastive":[86,103,130,138],"(DDGCL),":[88],"first":[90],"self-supervised":[91],"framework":[94,168],"on":[95,161],"graphs.":[97,236],"The":[98,181],"proposed":[99,223],"model":[100],"extends":[101],"idea":[105],"via":[109,164],"contrasting":[110],"two":[111,170],"nearby":[112],"temporal":[113],"views":[114],"same":[117],"node":[118],"identity,":[119],"time-dependent":[122],"similarity":[123],"critic.":[124],"Inspired":[125],"by":[126],"theoretical":[128],"developments":[129],"learning,":[131],"novel":[135],"GAN-type":[137],"loss":[139],"as":[140],"objective":[143],"order":[145],"correct":[147],"sampling":[149],"bias":[150],"occurred":[151],"negative":[153],"sample":[154],"construction":[155],"process.":[156],"We":[157],"conduct":[158],"extensive":[159],"experiments":[160],"benchmark":[162],"datasets":[163],"testing":[165],"DDGCL":[167],"under":[169,199],"different":[171],"self-supervision":[172,232],"schemes:":[173],"pretraining":[174],"finetuning":[176],"multi":[178],"task":[179],"learning.":[180],"results":[182],"show":[183],"that":[184,221],"using":[185],"simple":[187],"time-aware":[188],"GNN":[189],"encoder,":[190],"performance":[192,227],"downstream":[194],"tasks":[195],"is":[196],"significantly":[197],"improved":[198],"either":[200],"scheme":[201],"closely":[203],"match,":[204],"or":[205],"even":[206],"outperform":[207],"state-of-the-art":[208],"more":[213,226],"elegant":[214],"encoder":[215],"architectures.":[216],"Further":[217],"empirical":[218],"evaluations":[219],"suggest":[220],"approach":[224],"improvement":[228],"than":[229],"previously":[230],"established":[231],"mechanisms":[233],"over":[234],"static":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}