{"id":"https://openalex.org/W4399801173","doi":"https://doi.org/10.1109/tnet.2024.3415089","title":"Optimizing Task Placement and Online Scheduling for Distributed GNN Training Acceleration in Heterogeneous Systems","display_name":"Optimizing Task Placement and Online Scheduling for Distributed GNN Training Acceleration in Heterogeneous Systems","publication_year":2024,"publication_date":"2024-06-19","ids":{"openalex":"https://openalex.org/W4399801173","doi":"https://doi.org/10.1109/tnet.2024.3415089"},"language":"en","primary_location":{"id":"doi:10.1109/tnet.2024.3415089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnet.2024.3415089","pdf_url":null,"source":{"id":"https://openalex.org/S62238642","display_name":"IEEE/ACM Transactions on Networking","issn_l":"1063-6692","issn":["1063-6692","1558-2566"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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/ACM Transactions on Networking","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/A5048036564","display_name":"Ziyue Luo","orcid":"https://orcid.org/0000-0002-1253-8137"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ziyue Luo","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-1253-8137","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054679083","display_name":"Yixin Bao","orcid":"https://orcid.org/0000-0002-6921-2154"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yixin Bao","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-6921-2154","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012597518","display_name":"Chuan Wu","orcid":"https://orcid.org/0000-0002-3144-4398"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chuan Wu","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-3144-4398","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":2.5568,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89960334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"32","issue":"5","first_page":"3715","last_page":"3729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9327999949455261,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9327999949455261,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7308136224746704},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.619528591632843},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5943362712860107},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5511319041252136},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5359846353530884},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5188604593276978},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3302897810935974},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.14625123143196106},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08178606629371643},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07342082262039185},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.05411383509635925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7308136224746704},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.619528591632843},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5943362712860107},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5511319041252136},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5359846353530884},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5188604593276978},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3302897810935974},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.14625123143196106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08178606629371643},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07342082262039185},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.05411383509635925},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnet.2024.3415089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnet.2024.3415089","pdf_url":null,"source":{"id":"https://openalex.org/S62238642","display_name":"IEEE/ACM Transactions on Networking","issn_l":"1063-6692","issn":["1063-6692","1558-2566"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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/ACM Transactions on Networking","raw_type":"journal-article"},{"id":"pmh:oai:hub.hku.hk:10722/345696","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/345696","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6795446770","display_name":null,"funder_award_id":"C7004-22G (CRF)","funder_id":"https://openalex.org/F4320322887","funder_display_name":"The Research Council"},{"id":"https://openalex.org/G6813030023","display_name":null,"funder_award_id":"HKU 17207621","funder_id":"https://openalex.org/F4320322887","funder_display_name":"The Research Council"},{"id":"https://openalex.org/G7859864390","display_name":null,"funder_award_id":"17203522","funder_id":"https://openalex.org/F4320322887","funder_display_name":"The Research Council"}],"funders":[{"id":"https://openalex.org/F4320322887","display_name":"The Research Council","ror":"https://ror.org/03tcppy59"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1545728916","https://openalex.org/W1932742904","https://openalex.org/W2048971218","https://openalex.org/W2060393849","https://openalex.org/W2070232376","https://openalex.org/W2090891622","https://openalex.org/W2127827747","https://openalex.org/W2402144811","https://openalex.org/W2789335636","https://openalex.org/W2919897868","https://openalex.org/W2948777738","https://openalex.org/W2964571482","https://openalex.org/W2966878699","https://openalex.org/W2997636257","https://openalex.org/W3047002910","https://openalex.org/W3096566397","https://openalex.org/W3106803824","https://openalex.org/W3125783724","https://openalex.org/W3159109662","https://openalex.org/W3159953606","https://openalex.org/W3177554119","https://openalex.org/W3179205840","https://openalex.org/W3207941295","https://openalex.org/W4220807331","https://openalex.org/W4226353404","https://openalex.org/W6686509673","https://openalex.org/W6726873649","https://openalex.org/W6736685754","https://openalex.org/W6738144653","https://openalex.org/W6738964360","https://openalex.org/W6739693220","https://openalex.org/W6748799445","https://openalex.org/W6760045743","https://openalex.org/W6762211661","https://openalex.org/W6764171799","https://openalex.org/W6765543928","https://openalex.org/W6766978945","https://openalex.org/W6767710714","https://openalex.org/W6771625333","https://openalex.org/W6776488958","https://openalex.org/W6778729859","https://openalex.org/W6779909149","https://openalex.org/W6784425352","https://openalex.org/W6796463805","https://openalex.org/W6796909790","https://openalex.org/W6811326487"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Training":[0],"Graph":[1],"Neural":[2],"Networks":[3],"(GNNs)":[4],"on":[5,41],"large":[6,16,60],"graphs":[7],"is":[8],"resource-intensive":[9],"and":[10,39,76,84,97,103,121,138,160,165,187,190],"time-consuming,":[11],"mainly":[12],"due":[13],"to":[14,32,131,193,202],"the":[15,24,42,51,155,161,174],"graph":[17,37,61],"data":[18,62,101,162],"that":[19,153,172],"cannot":[20],"be":[21,33],"fit":[22],"into":[23],"memory":[25],"of":[26,67,93,100,124,145,157,176],"a":[27],"single":[28],"machine,":[29],"but":[30],"have":[31,106],"fetched":[34],"from":[35],"distributed":[36,45,54,125],"storage":[38],"processed":[40],"go.":[43],"Unlike":[44],"deep":[46],"neural":[47],"network":[48],"(DNN)":[49],"training,":[50],"bottleneck":[52],"in":[53,59,88,128,205],"GNN":[55,126],"training":[56,68,86,127,140,158,178,195],"lies":[57],"largely":[58],"transmission":[63,102,163],"for":[64,118],"constructing":[65],"mini-batches":[66],"samples.":[69],"Existing":[70],"solutions":[71],"often":[72],"advocate":[73],"data-computation":[74],"colocation,":[75],"do":[77],"not":[78,107],"work":[79],"well":[80,109],"with":[81,197],"limited":[82],"resources":[83],"heterogeneous":[85,89,129],"devices":[87],"clusters.":[90],"The":[91],"potentials":[92],"strategical":[94],"task":[95,104,119,169],"placement":[96,120,170,175],"optimal":[98],"scheduling":[99,123,151],"execution":[105,122,136,156],"been":[108],"explored.":[110],"This":[111],"paper":[112],"designs":[113],"an":[114,149,167],"efficient":[115],"algorithm":[116,152,199],"framework":[117,143],"systems,":[130],"better":[132],"resource":[133],"utilization,":[134],"improve":[135],"pipelining,":[137],"expedite":[139],"completion.":[141],"Our":[142],"consists":[144],"two":[146],"modules:":[147],"(i)":[148],"online":[150],"schedules":[154],"tasks,":[159],"plan;":[164],"(ii)":[166],"exploratory":[168],"scheme":[171],"decides":[173],"each":[177],"task.":[179],"We":[180],"conduct":[181],"thorough":[182],"theoretical":[183],"analysis,":[184],"testbed":[185,207],"experiments":[186],"simulation":[188],"studies,":[189],"observe":[191],"up":[192],"48%":[194],"speed-up":[196],"our":[198,206],"as":[200],"compared":[201],"representative":[203],"baselines":[204],"settings.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
