{"id":"https://openalex.org/W7105844470","doi":"https://doi.org/10.1109/access.2025.3633290","title":"GART: Graph Neural Network-Based Adaptive and Robust Task Scheduler for Heterogeneous Distributed Computing","display_name":"GART: Graph Neural Network-Based Adaptive and Robust Task Scheduler for Heterogeneous Distributed Computing","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7105844470","doi":"https://doi.org/10.1109/access.2025.3633290"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3633290","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3633290","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3633290","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shiyu Yang","orcid":"https://orcid.org/0009-0003-8173-5120"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shiyu Yang","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guanyu Ding","orcid":"https://orcid.org/0009-0000-2201-732X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanyu Ding","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zifan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zifan Chen","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jie Si Yang","orcid":"https://orcid.org/0000-0002-9826-4252"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Si Yang","raw_affiliation_strings":["The University of Utah, Salt Lake City, UT, USA"],"affiliations":[{"raw_affiliation_string":"The University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.4663,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95220154,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"200196","last_page":"200216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.6779999732971191,"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":0.6779999732971191,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.1843000054359436,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.025200000032782555,"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/scheduling","display_name":"Scheduling (production processes)","score":0.5634999871253967},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.555899977684021},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.5120999813079834},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.44670000672340393},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.37299999594688416},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.36980000138282776},{"id":"https://openalex.org/keywords/distributed-computing-environment","display_name":"Distributed Computing Environment","score":0.35429999232292175},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.34150001406669617},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.33880001306533813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8808000087738037},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.8014000058174133},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5634999871253967},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.5120999813079834},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C3739613","wikidata":"https://www.wikidata.org/wiki/Q679003","display_name":"Distributed Computing Environment","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34150001406669617},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C158207573","wikidata":"https://www.wikidata.org/wiki/Q5747224","display_name":"Heterogeneous network","level":4,"score":0.3264999985694885},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C77270119","wikidata":"https://www.wikidata.org/wiki/Q1655198","display_name":"Software-defined networking","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.25060001015663147},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3633290","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3633290","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bb37baa44b754bcfa1cc8635b19c8b2f","is_oa":true,"landing_page_url":"https://doaj.org/article/bb37baa44b754bcfa1cc8635b19c8b2f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 200196-200216 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3633290","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3633290","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5269380807876587,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"distributed":[1,83,87,205],"computing":[2,206],"systems":[3],"face":[4],"significant":[5],"challenges":[6],"in":[7,18,82,168,175,202,213],"achieving":[8],"optimal":[9,113],"resource":[10,52,108,176],"utilization":[11],"and":[12,50,75,95,107,140,150,178,195,208],"maintaining":[13],"performance":[14],"stability":[15],"when":[16],"operating":[17],"heterogeneous":[19,51,204],"cluster":[20,159],"environments":[21,207],"with":[22],"dynamic":[23,126],"workloads.":[24],"Existing":[25],"task":[26,80,88],"scheduling":[27,81,114,134],"approaches":[28],"often":[29],"rely":[30],"on":[31,156],"heuristic":[32],"rules":[33],"or":[34],"static":[35],"policies":[36,115],"that":[37,69,123,136,163],"fail":[38],"to":[39,41,102,125,182,186],"adapt":[40],"runtime":[42],"variations":[43],"such":[44],"as":[45,90],"node":[46,148,183],"failures,":[47],"load":[48,152],"fluctuations,":[49],"capacities.":[53],"To":[54],"address":[55],"these":[56],"limitations,":[57],"we":[58],"propose":[59],"GART":[60,85,164],"(Graph-based":[61],"Adaptive":[62],"Robust":[63],"Task":[64],"scheduling),":[65],"a":[66,97,132],"novel":[67],"framework":[68,111],"leverages":[70],"graph":[71],"neural":[72],"networks":[73],"(GNN)":[74],"reinforcement":[76,118],"learning":[77],"for":[78,211],"intelligent":[79],"systems.":[84,215],"models":[86],"workflows":[89],"directed":[91],"acyclic":[92],"graphs":[93],"(DAGs)":[94],"employs":[96],"specially":[98],"designed":[99],"GNN":[100],"architecture":[101],"capture":[103],"complex":[104],"inter-task":[105],"dependencies":[106],"requirements.":[109],"The":[110,197],"learns":[112],"through":[116],"deep":[117],"learning,":[119],"enabling":[120],"adaptive":[121],"decision-making":[122],"responds":[124],"system":[127],"conditions.":[128],"Our":[129],"approach":[130],"incorporates":[131],"robust":[133],"mechanism":[135],"maintains":[137],"high":[138],"throughput":[139],"low":[141],"latency":[142],"even":[143],"under":[144],"adverse":[145],"conditions":[146],"including":[147,190],"failures":[149,184],"sudden":[151],"spikes.":[153],"Extensive":[154],"experiments":[155],"the":[157],"Alibaba":[158],"trace":[160],"dataset":[161],"demonstrate":[162],"achieves":[165],"23.7%":[166],"improvement":[167],"average":[169],"job":[170],"completion":[171],"time,":[172],"31.4%":[173],"reduction":[174],"imbalance,":[177],"42.6%":[179],"better":[180],"resilience":[181],"compared":[185],"state-of-the-art":[187],"baseline":[188],"schedulers":[189],"Shortest":[191],"Job":[192],"First,":[193],"Tetrisched,":[194],"Decima.":[196],"results":[198],"validate":[199],"GART\u2019s":[200],"effectiveness":[201],"real-world":[203],"its":[209],"potential":[210],"deployment":[212],"production":[214]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-17T00:00:00"}