{"id":"https://openalex.org/W4225660637","doi":"https://doi.org/10.1109/tpds.2022.3205642","title":"Accelerating Backward Aggregation in GCN Training With Execution Path Preparing on GPUs","display_name":"Accelerating Backward Aggregation in GCN Training With Execution Path Preparing on GPUs","publication_year":2022,"publication_date":"2022-09-12","ids":{"openalex":"https://openalex.org/W4225660637","doi":"https://doi.org/10.1109/tpds.2022.3205642"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3205642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3205642","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.02662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048999092","display_name":"Shaoxian Xu","orcid":"https://orcid.org/0000-0001-7580-0668"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"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":"Shaoxian Xu","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","Zhejiang Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7580-0668","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066761150","display_name":"Zhiyuan Shao","orcid":"https://orcid.org/0000-0003-2139-6465"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"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":"Zhiyuan Shao","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","Zhejiang Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2139-6465","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102221206","display_name":"Ci Yang","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":"Ci Yang","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022398389","display_name":"Xiaofei Liao","orcid":"https://orcid.org/0000-0001-6302-813X"},"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":"Xiaofei Liao","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6302-813X","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022262922","display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"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":"Hai Jin","raw_affiliation_strings":["National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3934-7605","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab, School of Computer Science and Technology, 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":0.3936,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65145888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"33","issue":"12","first_page":"4891","last_page":"4902"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998000264167786,"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":0.9998000264167786,"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/T11478","display_name":"Caching and Content Delivery","score":0.991599977016449,"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"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8312471508979797},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6844799518585205},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.641285240650177},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5390732884407043},{"id":"https://openalex.org/keywords/on-the-fly","display_name":"On the fly","score":0.532107949256897},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5198824405670166},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4476449191570282},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4400789141654968},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4086523652076721},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3231203854084015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25512051582336426},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08822271227836609},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08012139797210693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312471508979797},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6844799518585205},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.641285240650177},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5390732884407043},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.532107949256897},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5198824405670166},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4476449191570282},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4400789141654968},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4086523652076721},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3231203854084015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25512051582336426},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08822271227836609},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08012139797210693}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2022.3205642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3205642","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2204.02662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.02662","pdf_url":"https://arxiv.org/pdf/2204.02662","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.02662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.02662","pdf_url":"https://arxiv.org/pdf/2204.02662","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"},{"score":0.41999998688697815,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1129710579","display_name":"\u57fa\u4e8e\u5b58\u5185\u8ba1\u7b97\u7684\u56fe\u8ba1\u7b97\u8f6f\u786c\u534f\u540c\u8bbe\u8ba1\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072195","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2465329715","display_name":null,"funder_award_id":"61832006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3607577353","display_name":"FPGA\u56fe\u8ba1\u7b97\u52a0\u901f\u5668\u7684\u6027\u80fd\u6269\u5c55\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61972444","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4565136922","display_name":null,"funder_award_id":"61825202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2000042664","https://openalex.org/W2042545849","https://openalex.org/W2087039607","https://openalex.org/W2098505406","https://openalex.org/W2164800850","https://openalex.org/W2271840356","https://openalex.org/W2294347342","https://openalex.org/W2484446135","https://openalex.org/W2523246573","https://openalex.org/W2718955078","https://openalex.org/W2755088640","https://openalex.org/W2768562455","https://openalex.org/W2782087530","https://openalex.org/W2790789009","https://openalex.org/W2800292742","https://openalex.org/W2807021761","https://openalex.org/W2896309423","https://openalex.org/W2939208918","https://openalex.org/W2941716445","https://openalex.org/W2951135776","https://openalex.org/W2951136539","https://openalex.org/W2961295589","https://openalex.org/W2964015378","https://openalex.org/W2964145825","https://openalex.org/W2971933740","https://openalex.org/W2981426507","https://openalex.org/W2984353870","https://openalex.org/W2996268457","https://openalex.org/W2997848713","https://openalex.org/W3007309629","https://openalex.org/W3035011799","https://openalex.org/W3035649237","https://openalex.org/W3037699692","https://openalex.org/W3084983693","https://openalex.org/W3094309150","https://openalex.org/W3100848837","https://openalex.org/W3132185085","https://openalex.org/W3164046276","https://openalex.org/W3175618977","https://openalex.org/W4288419263","https://openalex.org/W4294558607","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6694517276","https://openalex.org/W6713582119","https://openalex.org/W6726873649","https://openalex.org/W6727249380","https://openalex.org/W6738964360","https://openalex.org/W6744271739","https://openalex.org/W6760045743","https://openalex.org/W6761665040","https://openalex.org/W6764171799","https://openalex.org/W6765543928","https://openalex.org/W6766978945","https://openalex.org/W6767710714","https://openalex.org/W6771932116","https://openalex.org/W6779909149","https://openalex.org/W6780017182","https://openalex.org/W6784741312","https://openalex.org/W6797677657"],"related_works":["https://openalex.org/W2397288865","https://openalex.org/W2368524271","https://openalex.org/W4247116873","https://openalex.org/W2576709312","https://openalex.org/W2023657818","https://openalex.org/W2392797073","https://openalex.org/W2384907669","https://openalex.org/W2373120800","https://openalex.org/W4388654424","https://openalex.org/W2159668971"],"abstract_inverted_index":{"The":[0,231],"emerging":[1],"<italic":[2,123,184],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[3,124,185],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Graph":[4],"Convolutional":[5],"Network</i>":[6],"(GCN)":[7],"has":[8],"been":[9],"widely":[10],"used":[11,169],"in":[12,100,127,188,238],"many":[13],"domains,":[14],"where":[15],"it":[16],"is":[17],"important":[18],"to":[19,30,51,134,193,210,218,257,265],"improve":[20],"the":[21,31,53,59,67,147,166,195,207,228,250],"efficiencies":[22],"of":[23,37,70,88,117,146,174,252],"applications":[24],"by":[25,234,255],"accelerating":[26],"GCN":[27,42,102,236],"trainings.":[28],"Due":[29],"sparsity":[32],"nature":[33],"and":[34,72,164,177,263],"exploding":[35],"scales":[36],"input":[38,90,112,148],"real-world":[39,240],"graphs,":[40],"state-of-the-art":[41],"training":[43,103,108,172,197,237],"systems":[44,64],"(e.g.,":[45],"GNNAdvisor)":[46],"employ":[47],"graph":[48,60,78,136,167],"processing":[49,79,137],"techniques":[50],"accelerate":[52],"message":[54],"exchanging":[55],"(i.e.,":[56],"aggregations)":[57],"among":[58],"vertices.":[61],"Nevertheless,":[62],"these":[63],"treat":[65],"both":[66],"aggregation":[68,115],"stages":[69,116],"forward":[71],"backward":[73,118,175,196,229,253],"propagation":[74,119],"phases":[75,120],"as":[76,122,183,191,217,220,222],"all-active":[77],"procedures":[80],"that":[81,99,162,243],"indiscriminately":[82],"conduct":[83,140,194],"computations":[84,141],"on":[85,110,142,198,225,259,267],"all":[86],"vertices":[87,145],"an":[89,111,157],"graph.":[91,149],"In":[92],"this":[93,128,189],"article,":[94],"we":[95,155,201],"first":[96],"point":[97],"out":[98],"a":[101,106,153,203],"problem":[104],"with":[105,245],"given":[107],"set":[109],"graph,":[113],"its":[114],"(called":[121,182],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">backward":[125],"aggregations</i>":[126],"article)":[129,190],"can":[130],"be":[131],"equivalently":[132],"converted":[133],"partially-active":[135],"procedures,":[138],"which":[139],"only":[143],"partial":[144],"By":[150],"leveraging":[151],"such":[152],"finding,":[154],"propose":[156,202],"execution":[158,208],"path":[159],"preparing":[160],"method":[161],"collects":[163],"coalesces":[165],"data":[168],"during":[170,227],"different":[171],"layers":[173],"aggregations,":[176],"constructs":[178],"their":[179,212],"corresponding":[180],"sub-graphs":[181],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">execution":[186],"paths</i>":[187],"inputs":[192],"GPUs.":[199],"Further,":[200],"structural-aware":[204],"strategy":[205],"for":[206],"paths":[209],"compute":[211],"optimal":[213],"group":[214],"sizes,":[215],"so":[216],"gain":[219],"high":[221],"possible":[223],"performances":[224],"GPUs":[226],"aggregations.":[230],"experiment":[232],"results":[233],"conducting":[235],"typical":[239],"graphs":[241],"show":[242],"compared":[244],"GNNAdvisor,":[246],"our":[247],"approach":[248],"improves":[249],"performance":[251],"aggregations":[254],"up":[256,264],"5.68x":[258],"NVIDIA":[260,268],"P100":[261],"GPU,":[262],"6.57x":[266],"V100S":[269],"GPU":[270]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}