{"id":"https://openalex.org/W4388103722","doi":"https://doi.org/10.1145/3581784.3607040","title":"BLAD: Adaptive Load Balanced Scheduling and Operator Overlap Pipeline For Accelerating The Dynamic GNN Training","display_name":"BLAD: Adaptive Load Balanced Scheduling and Operator Overlap Pipeline For Accelerating The Dynamic GNN Training","publication_year":2023,"publication_date":"2023-10-30","ids":{"openalex":"https://openalex.org/W4388103722","doi":"https://doi.org/10.1145/3581784.3607040"},"language":"en","primary_location":{"id":"doi:10.1145/3581784.3607040","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581784.3607040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-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/A5037447327","display_name":"Kaihua Fu","orcid":"https://orcid.org/0000-0001-5117-7162"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaihua Fu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377840","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102754039","display_name":"Yuzhuo Yang","orcid":"https://orcid.org/0009-0003-7494-9219"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhuo Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020345102","display_name":"Jiuchen Shi","orcid":"https://orcid.org/0000-0002-5470-210X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuchen Shi","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323095","display_name":"Chao Li","orcid":"https://orcid.org/0000-0001-6218-4659"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037447327"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.5975,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84667167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9884999990463257,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9884999990463257,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9713000059127808,"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":0.7553905248641968},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.578673243522644},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5694390535354614},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5112993717193604},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4384500980377197},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.4327016770839691},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3931005895137787},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3539479374885559},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.24876224994659424},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20300999283790588},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13333946466445923},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07229164242744446},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.04421481490135193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7553905248641968},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.578673243522644},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5694390535354614},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5112993717193604},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4384500980377197},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.4327016770839691},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3931005895137787},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3539479374885559},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.24876224994659424},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20300999283790588},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13333946466445923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07229164242744446},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.04421481490135193},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":1,"locations":[{"id":"doi:10.1145/3581784.3607040","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581784.3607040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.699999988079071}],"awards":[{"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/G2857700228","display_name":null,"funder_award_id":"62232011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7942366687","display_name":null,"funder_award_id":"62022057","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2024565525","https://openalex.org/W2070232376","https://openalex.org/W2111708605","https://openalex.org/W2551706664","https://openalex.org/W2610034660","https://openalex.org/W2788708648","https://openalex.org/W2885195348","https://openalex.org/W2907492528","https://openalex.org/W2952179887","https://openalex.org/W2964571482","https://openalex.org/W2969388332","https://openalex.org/W2998313947","https://openalex.org/W3086238199","https://openalex.org/W3093570486","https://openalex.org/W3096566397","https://openalex.org/W3100346973","https://openalex.org/W3152893301","https://openalex.org/W3159109662","https://openalex.org/W3175110359","https://openalex.org/W3179429918","https://openalex.org/W3193327410","https://openalex.org/W3200735485","https://openalex.org/W3204508881","https://openalex.org/W3206504463","https://openalex.org/W3208777667","https://openalex.org/W3210361503","https://openalex.org/W4214540558","https://openalex.org/W4220807331","https://openalex.org/W4236099117","https://openalex.org/W4281401915","https://openalex.org/W4281689849","https://openalex.org/W4290877727","https://openalex.org/W4321445982","https://openalex.org/W4321636552"],"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":{"Dynamic":[0],"graph":[1,114],"networks":[2,16],"are":[3,97],"widely":[4],"used":[5],"for":[6],"learning":[7],"time-evolving":[8],"graphs,":[9],"but":[10],"prior":[11],"work":[12],"on":[13,103,136,139],"training":[14,57,137],"these":[15],"is":[17],"inefficient":[18],"due":[19],"to":[20,65,86,101,124,146],"communication":[21,33],"overhead,":[22],"long":[23],"synchronization,":[24],"and":[25,34,75,112],"poor":[26],"resource":[27],"usage.":[28],"Our":[29],"investigation":[30],"shows":[31],"that":[32,130],"synchronization":[35],"can":[36,52],"be":[37,53],"reduced":[38],"by":[39],"carefully":[40,99],"scheduling":[41],"the":[42,45,67,120,126],"workload.":[43],"And":[44],"execution":[46,122],"order":[47,123],"of":[48,108],"operators":[49,111],"in":[50,94],"GNNs":[51],"adjusted":[54],"without":[55,141],"hurting":[56],"convergence.":[58],"We":[59],"propose":[60],"a":[61,71,87,95,104],"system":[62],"called":[63],"BLAD":[64,131],"consider":[66],"above":[68],"factors,":[69],"comprising":[70],"two-level":[72],"load":[73],"scheduler":[74,81],"an":[76],"overlap-aware":[77],"topology":[78,117],"manager.":[79],"The":[80,92,116],"allocates":[82],"each":[83],"snapshot":[84],"group":[85,96],"GPU,":[88,105],"alleviating":[89],"cross-GPU":[90],"communication.":[91],"snapshots":[93],"then":[98],"allocated":[100],"processes":[102],"enabling":[106],"overlap":[107],"compute-intensive":[109],"NN":[110],"memory-intensive":[113],"operators.":[115],"manager":[118],"adjusts":[119],"operators'":[121],"maximize":[125],"overlap.":[127],"Experiments":[128],"show":[129],"achieves":[132],"27.2%":[133],"speed":[134],"up":[135],"time":[138],"average":[140],"affecting":[142],"final":[143],"accuracy,":[144],"compared":[145],"state-of-the-art":[147],"solutions.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}