{"id":"https://openalex.org/W4409257723","doi":"https://doi.org/10.1109/tkde.2025.3558641","title":"Scalable and Load-Balanced Full-Graph GNN Training on Multiple GPUs","display_name":"Scalable and Load-Balanced Full-Graph GNN Training on Multiple GPUs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409257723","doi":"https://doi.org/10.1109/tkde.2025.3558641"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2025.3558641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3558641","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5052641511","display_name":"Qiange Wang","orcid":"https://orcid.org/0000-0002-4847-6070"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qiange Wang","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4847-6070","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394256","display_name":"Yao Chen","orcid":"https://orcid.org/0000-0002-5798-2282"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yao Chen","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5798-2282","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023989495","display_name":"Weng\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-4281-2053"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weng-Fai Wong","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4281-2053","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039946576","display_name":"Bingsheng He","orcid":"https://orcid.org/0000-0001-8618-4581"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bingsheng He","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8618-4581","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.5427,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82170804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9929999709129333,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9700999855995178,"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":0.8715420961380005},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.707106351852417},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5660935044288635},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47517719864845276},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2652629315853119},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12117061018943787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8715420961380005},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.707106351852417},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5660935044288635},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47517719864845276},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2652629315853119},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12117061018943787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2025.3558641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3558641","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1596059437","https://openalex.org/W1926846071","https://openalex.org/W2006023152","https://openalex.org/W2070232376","https://openalex.org/W2469279958","https://openalex.org/W2548941637","https://openalex.org/W2600702321","https://openalex.org/W2604314403","https://openalex.org/W2798422034","https://openalex.org/W2969388332","https://openalex.org/W3096566397","https://openalex.org/W3106620263","https://openalex.org/W3129831491","https://openalex.org/W3133028082","https://openalex.org/W3157805807","https://openalex.org/W3159109662","https://openalex.org/W3159953606","https://openalex.org/W3198239267","https://openalex.org/W3205803342","https://openalex.org/W3206504463","https://openalex.org/W4220807331","https://openalex.org/W4281691175","https://openalex.org/W4281725510","https://openalex.org/W4288070868","https://openalex.org/W4318541522","https://openalex.org/W4321636549","https://openalex.org/W4381328668","https://openalex.org/W4389115441","https://openalex.org/W4392024605","https://openalex.org/W4396601684","https://openalex.org/W6684859321","https://openalex.org/W6690815549","https://openalex.org/W6703652217","https://openalex.org/W6713411898","https://openalex.org/W6726873649","https://openalex.org/W6727469013","https://openalex.org/W6728218750","https://openalex.org/W6738964360","https://openalex.org/W6745537798","https://openalex.org/W6754929296","https://openalex.org/W6756718674","https://openalex.org/W6760045743","https://openalex.org/W6764171799","https://openalex.org/W6767710714","https://openalex.org/W6776488958","https://openalex.org/W6779909149","https://openalex.org/W6787953186","https://openalex.org/W6791460281","https://openalex.org/W6796463805","https://openalex.org/W6809832721"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4401278057"],"abstract_inverted_index":{"While":[0],"full-graph":[1,46,136,187],"training":[2,16,48,63],"is":[3],"effective":[4],"for":[5,26],"graph":[6,141],"learning,":[7],"it":[8],"typically":[9],"demands":[10],"substantial":[11],"memory":[12,58,76,146],"resources.":[13],"Existing":[14],"multi-GPU":[15],"frameworks":[17],"struggle":[18],"with":[19,78,172],"scalability":[20],"because":[21],"they":[22],"require":[23],"retaining":[24],"data":[25,55,96,125,149,178],"each":[27],"layer":[28],"within":[29],"GPU":[30,162],"memory.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"present":[36],"<monospace":[37,51,81,110,128,166,195],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[38,52,82,111,129,167,196],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HongTu</monospace>,":[39],"a":[40,84,113,139,160],"memory-efficient":[41],"system":[42,189],"that":[43,64,117,144,165],"supports":[44],"out-of-memory":[45,135],"GNN":[47,188],"on":[49,159,191],"GPUs.":[50,72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HongTuoffloads</monospace>":[53],"vertex":[54],"to":[56,70,182,185,202],"CPU":[57,193],"and":[59,66,90,148,151],"employs":[60],"partition":[61,142],"parallelism":[62],"splits":[65],"assigns":[67],"large":[68],"graphs":[69,171],"multiple":[71],"To":[73,98],"reduce":[74],"runtime":[75],"consumption":[77,147],"optimal":[79],"performance,":[80],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HongTuutilizes</monospace>":[83],"hybrid":[85],"solution":[86],"combining":[87],"recomputation,":[88],"caching,":[89],"computation-reordering,":[91],"enabling":[92],"efficient":[93,123],"layer-wise":[94],"intermediate":[95],"management.":[97],"address":[99],"the":[100,131,153,186],"increased":[101],"communication":[102,115,156,179],"caused":[103],"by":[104,180],"duplicated":[105],"neighbor":[106],"access":[107],"among":[108],"partitions,":[109],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HongTuemploys</monospace>":[112],"deduplicated":[114],"framework":[116],"converts":[118],"host-GPU":[119,177],"transfers":[120],"into":[121],"more":[122],"inter/intra-GPU":[124],"access.":[126],"Additionally,":[127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HongTutackles</monospace>":[130],"load-imbalance":[132],"issues":[133],"in":[134],"training,":[137],"featuring":[138],"multi-objective":[140],"algorithm":[143],"balances":[145],"transfer":[150],"maximizes":[152],"effectiveness":[154],"of":[155],"deduplication.":[157],"Experiments":[158],"4\u00d7A100":[161],"server":[163],"show":[164],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HongTucan</monospace>":[168],"effectively":[169],"train":[170],"billion":[173],"edges":[174],"while":[175],"reducing":[176],"25%":[181],"71%.":[183],"Compared":[184],"running":[190],"16":[192],"nodes,":[194],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HongTuachieves</monospace>":[197],"speedups":[198],"ranging":[199],"from":[200],"11.4\u00d7":[201],"21.3\u00d7.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
