{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:35:51Z","timestamp":1773772551627,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3633290","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:42:17Z","timestamp":1763404937000},"page":"200196-200216","source":"Crossref","is-referenced-by-count":5,"title":["GART: Graph Neural Network-Based Adaptive and Robust Task Scheduler for Heterogeneous Distributed Computing"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8173-5120","authenticated-orcid":false,"given":"Shiyu","family":"Yang","sequence":"first","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2201-732X","authenticated-orcid":false,"given":"Guanyu","family":"Ding","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}]},{"given":"Zifan","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9826-4252","authenticated-orcid":false,"given":"Jie","family":"Si Yang","sequence":"additional","affiliation":[{"name":"The University of Utah, Salt Lake City, UT, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2934664"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465386"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626334"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2644865.2541941"},{"key":"ref7","first-page":"24","article-title":"Dominant resource fairness: Fair allocation of multiple resource types","volume-title":"Proc. 8th USENIX Conf. Networked Syst. Design Implement.","author":"Ghodsi"},{"key":"ref8","first-page":"295","article-title":"Mesos: A platform for fine-grained resource sharing in the data center","volume-title":"Proc. 8th USENIX Conf. Networked Syst. Design Implement.","author":"Hindman"},{"key":"ref9","article-title":"Towards understanding heterogeneous clouds at scale: Google trace analysis","author":"Reiss","year":"2012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901355"},{"key":"ref11","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Jeon"},{"key":"ref12","first-page":"1","article-title":"Optimus: An efficient dynamic resource scheduler for deep learning clusters","volume-title":"Proc. 14th EuroSys Conf.","author":"Zhang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref14","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Mirhoseini"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WORKS.2008.4723958"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/escience.2012.6404430"},{"key":"ref17","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref18","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Hamilton"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref20","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref21","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Veli\u010dkovi\u0107"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"ref24","first-page":"293","article-title":"Making sense of performance in data analytics frameworks","volume-title":"Proc. 5th ACM Symp. Cloud Comput.","author":"Ousterhout"},{"key":"ref25","first-page":"499","article-title":"Hawk: Hybrid datacenter scheduling","volume-title":"Proc. 6th ACM Symp. Cloud Comput.","author":"Delgado"},{"key":"ref26","first-page":"81","article-title":"GRAPHENE: Packing and dependency-aware scheduling for data-parallel clusters","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Design Implement.","author":"Grandl"},{"key":"ref27","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref30","first-page":"50","article-title":"A deep reinforcement learning perspective on Internet congestion control","volume-title":"Proc. ACM Special Interest Group Data Commun.","author":"Jay"},{"key":"ref31","first-page":"143","article-title":"DistCache: Provable load balancing for large-scale storage systems with distributed caching","volume-title":"Proc. 17th USENIX Symp. Networked Syst. Design Implement.","author":"Liu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref35","first-page":"94","article-title":"Building scalable and flexible cluster managers using declarative programming","volume-title":"Proc. Workshop Hot Topics Operating Syst.","author":"Vuppalapati"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522716"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2490301.2451125"},{"issue":"11","key":"ref39","first-page":"4117","article-title":"Thermal-aware task scheduling using graph attention networks in heterogeneous computing systems","volume":"41","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Comput.-Aided Design Integr. Circuits Syst."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3526239"},{"key":"ref41","first-page":"15580","article-title":"Exact combinatorial optimization with graph convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gasse"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000405"},{"key":"ref43","first-page":"87","article-title":"A survey of scheduling frameworks in big data systems","volume":"115","author":"Liu","year":"2021","journal-title":"Future Gener. Comput. Syst."},{"issue":"12","key":"ref44","first-page":"3812","article-title":"Deep reinforcement learning based multi-objective scheduling for distributed computing systems","volume":"33","author":"Wang","year":"2022","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/s25082428"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2006.1662383"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-007-0135-3"},{"key":"ref48","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2941458"},{"key":"ref50","first-page":"945","article-title":"MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Design Implement.","author":"Weng"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/sym17071109"},{"key":"ref52","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"issue":"1","key":"ref53","first-page":"1213","article-title":"Time-regularized interrupting options","volume":"19","author":"Mankowitz","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2004.1392606"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cloud.2010.26"},{"issue":"3","key":"ref56","first-page":"293","article-title":"Fault tolerance-challenges, techniques and implementation in cloud computing","volume":"27","author":"Bala","year":"2015","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"issue":"9","key":"ref57","first-page":"14","article-title":"Proactive fault tolerance approach to increase reliability of cloud service","volume":"135","author":"Gupta","year":"2016","journal-title":"Int. J. Comput. Appl."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2012.2221934"},{"key":"ref59","author":"Group","year":"2018","journal-title":"Alibaba Cluster Trace Program"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11250527.pdf?arnumber=11250527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:40Z","timestamp":1764787420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11250527\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3633290","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}