{"id":"https://openalex.org/W4402043139","doi":"https://doi.org/10.14778/3681954.3681968","title":"Eliminating Data Processing Bottlenecks in GNN Training over Large Graphs via Two-level Feature Compression","display_name":"Eliminating Data Processing Bottlenecks in GNN Training over Large Graphs via Two-level Feature Compression","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4402043139","doi":"https://doi.org/10.14778/3681954.3681968"},"language":"en","primary_location":{"id":"doi:10.14778/3681954.3681968","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3681968","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5111996979","display_name":"Yuxin Ma","orcid":"https://orcid.org/0009-0006-7553-7277"},"institutions":[{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Yuxin Ma","raw_affiliation_strings":["USTC"],"affiliations":[{"raw_affiliation_string":"USTC","institution_ids":["https://openalex.org/I91090688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092997992","display_name":"Ping Gong","orcid":"https://orcid.org/0009-0001-4486-3495"},"institutions":[{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Ping Gong","raw_affiliation_strings":["USTC"],"affiliations":[{"raw_affiliation_string":"USTC","institution_ids":["https://openalex.org/I91090688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109188050","display_name":"Tianming Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Tianming Wu","raw_affiliation_strings":["USTC"],"affiliations":[{"raw_affiliation_string":"USTC","institution_ids":["https://openalex.org/I91090688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082848169","display_name":"Jiawei Yi","orcid":"https://orcid.org/0000-0003-0325-7146"},"institutions":[{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Jiawei Yi","raw_affiliation_strings":["USTC"],"affiliations":[{"raw_affiliation_string":"USTC","institution_ids":["https://openalex.org/I91090688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000734067","display_name":"Chengru Yang","orcid":"https://orcid.org/0009-0003-4320-0723"},"institutions":[{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Chengru Yang","raw_affiliation_strings":["USTC"],"affiliations":[{"raw_affiliation_string":"USTC","institution_ids":["https://openalex.org/I91090688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354226","display_name":"Cheng Li","orcid":"https://orcid.org/0000-0001-7064-6120"},"institutions":[{"id":"https://openalex.org/I4210137491","display_name":"National Science Center","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"funder","lineage":["https://openalex.org/I4210137491"]},{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Cheng Li","raw_affiliation_strings":["USTC and Institute of Artificial Intelligence, Hefei Comprehensive National Science Center"],"affiliations":[{"raw_affiliation_string":"USTC and Institute of Artificial Intelligence, Hefei Comprehensive National Science Center","institution_ids":["https://openalex.org/I4210137491","https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078006690","display_name":"Qirong Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111635","display_name":"Earthquake Planning and Protection Organization","ror":"https://ror.org/01zy7ja20","country_code":"GR","type":"government","lineage":["https://openalex.org/I4210111635"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Qirong Peng","raw_affiliation_strings":["OPPO"],"affiliations":[{"raw_affiliation_string":"OPPO","institution_ids":["https://openalex.org/I4210111635"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113430402","display_name":"Guiming Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111635","display_name":"Earthquake Planning and Protection Organization","ror":"https://ror.org/01zy7ja20","country_code":"GR","type":"government","lineage":["https://openalex.org/I4210111635"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Guiming Xie","raw_affiliation_strings":["OPPO"],"affiliations":[{"raw_affiliation_string":"OPPO","institution_ids":["https://openalex.org/I4210111635"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113357777","display_name":"Yongcheng Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111635","display_name":"Earthquake Planning and Protection Organization","ror":"https://ror.org/01zy7ja20","country_code":"GR","type":"government","lineage":["https://openalex.org/I4210111635"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yongcheng Bao","raw_affiliation_strings":["OPPO"],"affiliations":[{"raw_affiliation_string":"OPPO","institution_ids":["https://openalex.org/I4210111635"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325566","display_name":"Haifeng Liu","orcid":"https://orcid.org/0000-0003-0861-4966"},"institutions":[{"id":"https://openalex.org/I4210111635","display_name":"Earthquake Planning and Protection Organization","ror":"https://ror.org/01zy7ja20","country_code":"GR","type":"government","lineage":["https://openalex.org/I4210111635"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Haifeng Liu","raw_affiliation_strings":["OPPO"],"affiliations":[{"raw_affiliation_string":"OPPO","institution_ids":["https://openalex.org/I4210111635"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113315413","display_name":"Yinlong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Yinlong Xu","raw_affiliation_strings":["USTC"],"affiliations":[{"raw_affiliation_string":"USTC","institution_ids":["https://openalex.org/I91090688"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5111996979"],"corresponding_institution_ids":["https://openalex.org/I91090688"],"apc_list":null,"apc_paid":null,"fwci":2.5459,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90795593,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"17","issue":"11","first_page":"2854","last_page":"2866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9961000084877014,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8522343635559082},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.738139271736145},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6679673194885254},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.552483081817627},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5433775186538696},{"id":"https://openalex.org/keywords/rounding","display_name":"Rounding","score":0.5047656297683716},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.49485963582992554},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4915376603603363},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48574572801589966},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4362882375717163},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4335390031337738},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.420291006565094},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35963183641433716},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3553815484046936},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3425367474555969},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27507686614990234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22537949681282043},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.11013886332511902},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09443861246109009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8522343635559082},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.738139271736145},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6679673194885254},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.552483081817627},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5433775186538696},{"id":"https://openalex.org/C136625980","wikidata":"https://www.wikidata.org/wiki/Q663208","display_name":"Rounding","level":2,"score":0.5047656297683716},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.49485963582992554},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4915376603603363},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48574572801589966},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4362882375717163},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4335390031337738},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.420291006565094},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35963183641433716},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3553815484046936},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3425367474555969},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27507686614990234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22537949681282043},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.11013886332511902},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09443861246109009},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"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/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3681954.3681968","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3681968","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1953691509","https://openalex.org/W2049266248","https://openalex.org/W2052440657","https://openalex.org/W2113158412","https://openalex.org/W2116873850","https://openalex.org/W2142265837","https://openalex.org/W2799900537","https://openalex.org/W3002924435","https://openalex.org/W3087202534","https://openalex.org/W3090369187","https://openalex.org/W3096566397","https://openalex.org/W3104001151","https://openalex.org/W3117528324","https://openalex.org/W3159894882","https://openalex.org/W3159953606","https://openalex.org/W3167254314","https://openalex.org/W3176940011","https://openalex.org/W3211235328","https://openalex.org/W3214554319","https://openalex.org/W4220807331","https://openalex.org/W4315977496","https://openalex.org/W4380091476","https://openalex.org/W4381328689","https://openalex.org/W4386260592","https://openalex.org/W4387321131","https://openalex.org/W6863951927"],"related_works":["https://openalex.org/W2147122795","https://openalex.org/W2061075966","https://openalex.org/W3147501184","https://openalex.org/W2167303720","https://openalex.org/W2268996566","https://openalex.org/W2109715593","https://openalex.org/W3161817247","https://openalex.org/W2012518269","https://openalex.org/W2068309140","https://openalex.org/W4239937081"],"abstract_inverted_index":{"Training":[0],"GNNs":[1],"over":[2],"large":[3,165],"graphs":[4],"faces":[5],"a":[6,26,41,60,114,174],"severe":[7],"data":[8],"processing":[9],"bottleneck,":[10],"involving":[11],"both":[12],"sampling":[13],"and":[14,70,82,130,160,181,188,192,201],"feature":[15,32,44,91],"loading.":[16],"To":[17,34],"tackle":[18],"this":[19,78],"issue,":[20],"we":[21,39,94],"introduce":[22],"F":[23,105,152,170],"2":[24,106,153,171],"CGT,":[25],"fast":[27],"GNN":[28,158,183],"training":[29,89,103,184],"system":[30],"incorporating":[31],"compression.":[33,92],"avoid":[35],"potential":[36],"accuracy":[37,68,85,203],"degradation,":[38],"propose":[40],"two-level,":[42],"hybrid":[43],"compression":[45,50,65,175],"approach":[46,79],"that":[47,77,169],"applies":[48],"different":[49],"methods":[51],"to":[52,121,179,198],"various":[53,138],"graph":[54,124,141],"nodes.":[55],"This":[56],"differentiated":[57],"choice":[58],"strikes":[59],"balance":[61],"between":[62],"rounding":[63],"errors,":[64],"ratios,":[66],"model":[67,84],"loss,":[69],"preprocessing":[71],"costs.":[72],"Our":[73],"theoretical":[74],"analysis":[75],"proves":[76],"offers":[80],"convergence":[81],"comparable":[83],"as":[86],"the":[87,97,133],"conventional":[88],"without":[90],"Additionally,":[93],"also":[95],"co-design":[96],"on-GPU":[98],"cache":[99,110,119,145],"sub-system":[100],"with":[101,126,196],"compression-enabled":[102],"within":[104],"CGT.":[107],"The":[108],"new":[109,118],"sub-system,":[111],"driven":[112],"by":[113],"cost":[115],"model,":[116],"runs":[117],"policies":[120],"carefully":[122],"choose":[123],"nodes":[125],"high":[127],"access":[128],"frequencies,":[129],"well":[131],"partitions":[132],"spare":[134],"GPU":[135],"memory":[136],"for":[137,143,190],"types":[139],"of":[140,151,177,186],"data,":[142],"improving":[144],"hit":[146],"rates.":[147],"Finally,":[148],"extensive":[149],"evaluation":[150],"CGT":[154,172],"on":[155],"two":[156],"popular":[157],"models":[159],"four":[161],"datasets,":[162,167],"including":[163],"three":[164],"public":[166],"demonstrates":[168],"achieves":[173],"ratio":[176],"up":[178,197],"128":[180],"provides":[182],"speedups":[185],"1.23-2.56\u00d7":[187],"3.58--71.46\u00d7":[189],"single-machine":[191],"distributed":[193],"training,":[194],"respectively,":[195],"32":[199],"GPUs":[200],"marginal":[202],"loss.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}