{"id":"https://openalex.org/W4415709612","doi":"https://doi.org/10.1109/icme59968.2025.11209980","title":"HeteroGNN: A Heterogeneous Stage Division Based GNN Training Framework to Maximize CPU-GPU Parallelism","display_name":"HeteroGNN: A Heterogeneous Stage Division Based GNN Training Framework to Maximize CPU-GPU Parallelism","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709612","doi":"https://doi.org/10.1109/icme59968.2025.11209980"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103023369","display_name":"Xiangrui Yang","orcid":"https://orcid.org/0009-0008-7655-1948"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangrui Yang","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015697606","display_name":"Zhihao Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Zeng","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104077301","display_name":"Jiawei Yang","orcid":"https://orcid.org/0009-0006-4259-7847"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Yang","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023330648","display_name":"Yekang Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yekang Zhan","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065846003","display_name":"Qiang Cao","orcid":"https://orcid.org/0000-0001-9124-0533"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Cao","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102838219","display_name":"Jie Yao","orcid":"https://orcid.org/0009-0007-6470-7063"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Yao","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34902635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.5825999975204468,"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"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.5825999975204468,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.18150000274181366,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.07859999686479568,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/partition","display_name":"Partition (number theory)","score":0.6723999977111816},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6435999870300293},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5841000080108643},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5306000113487244},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5159000158309937},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.487199991941452},{"id":"https://openalex.org/keywords/division","display_name":"Division (mathematics)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4652000069618225},{"id":"https://openalex.org/keywords/dependency-graph","display_name":"Dependency graph","score":0.46239998936653137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8307999968528748},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6723999977111816},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6435999870300293},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C60798267","wikidata":"https://www.wikidata.org/wiki/Q1226939","display_name":"Division (mathematics)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.46239998936653137},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46050000190734863},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.3824999928474426},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3343000113964081},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.257099986076355},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":8,"referenced_works":["https://openalex.org/W3097300053","https://openalex.org/W3130660608","https://openalex.org/W3132185085","https://openalex.org/W4321446145","https://openalex.org/W4372267520","https://openalex.org/W4392791736","https://openalex.org/W4402979612","https://openalex.org/W4404047373"],"related_works":[],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4],"become":[5],"inevitable":[6],"tools":[7],"for":[8,127],"extracting":[9],"knowledge":[10],"from":[11],"massive":[12],"topological":[13],"structure":[14],"data.":[15],"However,":[16],"experimental":[17],"observation":[18],"shows":[19],"that":[20,153],"existing":[21],"GNN":[22,73,80,119,166],"training":[23,39,61,74,81,158],"frameworks":[24],"exhibit":[25],"low":[26],"efficiency":[27],"when":[28],"performing":[29],"memory-access-intensive":[30],"data":[31,48],"preparation":[32],"stage":[33,40,92],"upon":[34,41,82,143],"CPU":[35,128],"and":[36,55,129,169,176],"computation-intensive":[37],"model":[38],"GPU.":[42,130],"This":[43],"is":[44],"largely":[45],"due":[46],"to":[47,76,100,103,146,161,164,171,174],"dependency":[49],"restriction":[50],"between":[51],"the":[52,97,141],"two":[53,98],"stages":[54,99],"sequential":[56],"execution":[57],"of":[58,79],"computation":[59,112],"in":[60],"iterations.":[62],"Based":[63],"on":[64],"these":[65],"observations,":[66],"this":[67],"paper":[68],"proposes":[69,89],"HeteroGNN,":[70],"an":[71,134],"efficient":[72],"framework,":[75,167],"maximize":[77,147],"parallelism":[78],"heterogeneous":[83],"CPU-GPU":[84],"architecture.":[85],"Specifically,":[86],"HeteroGNN":[87,108,132,154],"first":[88],"a":[90,110],"data-dependency-aware":[91],"division":[93],"policy,":[94],"which":[95,115,138],"divides":[96],"six":[101,144],"phases":[102,145],"offer":[104],"inter-stage":[105],"parallelism.":[106],"Further,":[107],"establishes":[109],"fine-grained":[111],"partition":[113],"schema,":[114],"actively":[116],"partitions":[117],"typical":[118],"computing":[120],"operations":[121],"into":[122],"multiple":[123],"schedulable":[124],"tasks":[125,142],"suitable":[126],"Finally,":[131],"designs":[133],"adaptive":[135],"task":[136],"scheduler,":[137],"adaptively":[139],"schedules":[140],"GPU":[148],"efficiency.":[149],"Experiment":[150],"results":[151],"demonstrate":[152],"speeds":[155],"up":[156,160],"end-to-end":[157],"time":[159],"1.29\u00d7":[162],"comparing":[163,173],"state-of-the-art":[165],"PiPAD,":[168],"1.30\u00d7":[170],"2.06\u00d7":[172],"DGL":[175],"PyG.":[177]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}