{"id":"https://openalex.org/W4388662082","doi":"https://doi.org/10.1145/3581784.3607056","title":"DistTGL: Distributed Memory-Based Temporal Graph Neural Network Training","display_name":"DistTGL: Distributed Memory-Based Temporal Graph Neural Network Training","publication_year":2023,"publication_date":"2023-11-11","ids":{"openalex":"https://openalex.org/W4388662082","doi":"https://doi.org/10.1145/3581784.3607056"},"language":"en","primary_location":{"id":"doi:10.1145/3581784.3607056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607056","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607056","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 International Conference for High Performance Computing, Networking, Storage and Analysis","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/10.1145/3581784.3607056","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009003549","display_name":"Hongkuan Zhou","orcid":"https://orcid.org/0000-0001-8158-3081"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hongkuan Zhou","raw_affiliation_strings":["University of Southern California, Los Angeles, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, United States of America","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060763203","display_name":"Da Zheng","orcid":"https://orcid.org/0000-0001-8115-5415"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Da Zheng","raw_affiliation_strings":["AWS AI, Santa Clara, United States of America"],"affiliations":[{"raw_affiliation_string":"AWS AI, Santa Clara, United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675531","display_name":"Xiang Song","orcid":"https://orcid.org/0000-0001-5030-5054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Song","raw_affiliation_strings":["AWS AI, Santa Clara, United States of America"],"affiliations":[{"raw_affiliation_string":"AWS AI, Santa Clara, United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082384108","display_name":"George Karypis","orcid":"https://orcid.org/0000-0003-2753-1437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Karypis","raw_affiliation_strings":["AWS AI, Santa Clara, United States of America"],"affiliations":[{"raw_affiliation_string":"AWS AI, Santa Clara, United States of America","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033166029","display_name":"Viktor K. Prasanna","orcid":"https://orcid.org/0000-0002-1609-8589"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor Prasanna","raw_affiliation_strings":["University of Southern California, Los Angeles, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, United States of America","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009003549"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":3.1109,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93297678,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998999834060669,"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":0.9998999834060669,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9980999827384949,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9936000108718872,"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":0.8828679323196411},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7531722784042358},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7257076501846313},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5839945673942566},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5117332935333252},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.48196861147880554},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.42664211988449097},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42559683322906494},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3590407967567444},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33755022287368774},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33474743366241455},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08379057049751282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8828679323196411},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7531722784042358},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7257076501846313},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5839945673942566},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5117332935333252},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.48196861147880554},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.42664211988449097},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42559683322906494},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3590407967567444},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33755022287368774},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33474743366241455},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08379057049751282},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581784.3607056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607056","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607056","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 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581784.3607056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607056","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607056","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 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6077084736","display_name":null,"funder_award_id":"OAC-2209563","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G805653150","display_name":"OAC Core: Scalable Graph ML on Distributed Heterogeneous Systems","funder_award_id":"2209563","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388662082.pdf","grobid_xml":"https://content.openalex.org/works/W4388662082.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2593168194","https://openalex.org/W2965683718","https://openalex.org/W2998116985","https://openalex.org/W3104001151","https://openalex.org/W3109841242","https://openalex.org/W3159109662","https://openalex.org/W3159953606","https://openalex.org/W3166605255","https://openalex.org/W3200735485","https://openalex.org/W4221155008","https://openalex.org/W4281689849","https://openalex.org/W4283314525","https://openalex.org/W4283366315","https://openalex.org/W4290877727","https://openalex.org/W4290944486","https://openalex.org/W4321445982"],"related_works":["https://openalex.org/W2359328895","https://openalex.org/W2007402811","https://openalex.org/W2363535981","https://openalex.org/W2326762630","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2391354408","https://openalex.org/W2166562438","https://openalex.org/W98480971","https://openalex.org/W2150291671"],"abstract_inverted_index":{"Memory-based":[0],"Temporal":[1],"Graph":[2],"Neural":[3],"Networks":[4],"are":[5],"powerful":[6],"tools":[7],"in":[8,18,34,77,133,137],"dynamic":[9],"graph":[10,35],"representation":[11],"learning":[12],"and":[13,37,89,115,135],"have":[14],"demonstrated":[15],"superior":[16],"performance":[17],"many":[19],"real-world":[20],"applications.":[21],"However,":[22],"their":[23],"node":[24,68],"memory":[25,69],"favors":[26],"smaller":[27],"batch":[28],"sizes":[29],"to":[30,39,57,73,92],"capture":[31],"more":[32],"dependencies":[33],"events":[36],"needs":[38],"be":[40],"maintained":[41],"synchronously":[42],"across":[43],"all":[44],"trainers.":[45],"As":[46],"a":[47,111],"result,":[48],"existing":[49,105],"frameworks":[50],"suffer":[51],"from":[52],"accuracy":[53,134],"loss":[54],"when":[55],"scaling":[56],"multiple":[58],"GPUs.":[59],"Even":[60],"worse,":[61],"the":[62,67,75,127],"tremendous":[63],"overhead":[64],"of":[65],"synchronizing":[66],"makes":[70],"it":[71],"impractical":[72],"deploy":[74],"solution":[76,91],"GPU":[78,98],"clusters.":[79,99],"In":[80,119],"this":[81],"work,":[82],"we":[83],"propose":[84],"DistTGL":[85,100,121],"---":[86],"an":[87,107,116],"efficient":[88],"scalable":[90],"train":[93],"memory-based":[94],"TGNNs":[95],"on":[96],"distributed":[97],"has":[101],"three":[102],"improvements":[103],"over":[104],"solutions:":[106],"enhanced":[108],"TGNN":[109],"model,":[110],"novel":[112],"training":[113,138],"algorithm,":[114],"optimized":[117],"system.":[118],"experiments,":[120],"achieves":[122],"near-linear":[123],"convergence":[124],"speedup,":[125],"outperforming":[126],"state-of-the-art":[128],"single-machine":[129],"method":[130],"by":[131],"14.5%":[132],"10.17\u00d7":[136],"throughput.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}