{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:21:41Z","timestamp":1783700501073,"version":"3.55.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62132019"],"award-info":[{"award-number":["62132019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62102392"],"award-info":[{"award-number":["62102392"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Projects of Zhejiang Laboratory","award":["2022QA0AB04"],"award-info":[{"award-number":["2022QA0AB04"]}]},{"DOI":"10.13039\/501100004608","name":"National Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20210121"],"award-info":[{"award-number":["BK20210121"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association of CAS","doi-asserted-by":"publisher","award":["2023481"],"award-info":[{"award-number":["2023481"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tnet.2023.3244794","type":"journal-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T18:37:39Z","timestamp":1677091059000},"page":"2267-2280","source":"Crossref","is-referenced-by-count":53,"title":["GRID: Gradient Routing With In-Network Aggregation for Distributed Training"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4222-1971","authenticated-orcid":false,"given":"Jin","family":"Fang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1311-8908","authenticated-orcid":false,"given":"Gongming","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3831-4577","authenticated-orcid":false,"given":"Hongli","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changbo","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuolong","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3485983.3494853"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155282"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2656877.2656890"},{"key":"ref15","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2017","journal-title":"arXiv 1712 01887"},{"key":"ref59","first-page":"1223","article-title":"Large scale distributed deep networks","volume":"25","author":"dean","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"1","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume":"30","author":"alistarh","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","year":"2021","journal-title":"Pulp"},{"key":"ref53","year":"2022","journal-title":"Mellanox and NVIDIA"},{"key":"ref52","year":"2021","journal-title":"Intel Tofino2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2947013"},{"key":"ref55","first-page":"829","article-title":"In-network aggregation for shared machine learning clusters","volume":"3","author":"gebara","year":"2021","journal-title":"Proc Mach Learn Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref54","year":"2022","journal-title":"NetFPGA"},{"key":"ref17","first-page":"363","article-title":"E3: Energy-efficient microservices on SmartNIC-accelerated servers","author":"liu","year":"2019","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref16","first-page":"1","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","volume":"30","author":"wen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472887"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472940"},{"key":"ref51","first-page":"3","article-title":"Camdoop: Exploiting in-network aggregation for big data applications","author":"costa","year":"2012","journal-title":"Proc 9th USENIX Conf Networked Syst Design Implement"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2674005.2674996"},{"key":"ref46","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","author":"jiang","year":"2020","journal-title":"Proc of USENIX Symp on Operating Systems Design and Implementation (OSDI)"},{"key":"ref45","first-page":"172","article-title":"Blink: Fast and generic collectives for distributed ML","volume":"2","author":"wang","year":"2020","journal-title":"Proc Mach Learn Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/940923.940937"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2185448.2185474"},{"key":"ref42","article-title":"Bandwidth reduction using importance weighted pruning on ring AllReduce","author":"cheng","year":"2019","journal-title":"arXiv 1901 01544"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref44","first-page":"132","article-title":"Priority-based parameter propagation for distributed DNN training","author":"jayarajan","year":"2019","journal-title":"Proc Mach Learn Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"ref49","first-page":"6869","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"hubara","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref8","first-page":"418","article-title":"TicTac: Accelerating distributed deep learning with communication scheduling","volume":"1","author":"hashemi","year":"2019","journal-title":"Proc Mach Learn Syst"},{"key":"ref7","first-page":"785","article-title":"Scaling distributed machine learning with in-network aggregation","author":"sapio","year":"2021","journal-title":"Proc 18th USENIX Symp Networked Syst Design Implement (NSDI)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3076687"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3096846"},{"key":"ref3","first-page":"1","article-title":"Deep learning based recommender system: A survey and new perspectives","volume":"52","author":"shuai","year":"2017","journal-title":"ACM Comput Surv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"ref5","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","author":"lao","year":"2021","journal-title":"Proc NSDI"},{"key":"ref40","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"sergeev","year":"2018","journal-title":"arXiv 1802 05799"},{"key":"ref35","first-page":"456","article-title":"Distributed training strategies for the structured perceptron","author":"mcdonald","year":"2010","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref34","first-page":"1","article-title":"Parallelized stochastic gradient descent","volume":"23","author":"zinkevich","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"1","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","volume":"31","author":"chen","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011544"},{"key":"ref31","article-title":"Cooperative SGD: A unified framework for the design and analysis of communication-efficient SGD algorithms","author":"wang","year":"2018","journal-title":"arXiv 1808 07576"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2906743"},{"key":"ref30","first-page":"212","article-title":"Adaptive communication strategies to achieve the best error-runtime trade-off in local-update SGD","volume":"1","author":"wang","year":"2019","journal-title":"Proc Mach Learn Syst"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ISCC50000.2020.9219732"},{"key":"ref33","first-page":"1","article-title":"DETOX: A redundancy-based framework for faster and more robust gradient aggregation","volume":"32","author":"rajput","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"1","article-title":"Pipe-SGD: A decentralized pipelined SGD framework for distributed deep net training","volume":"31","author":"li","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref38","first-page":"1","article-title":"PowerSGD: Practical low-rank gradient compression for distributed optimization","volume":"32","author":"vogels","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref71","year":"2023","journal-title":"Behavioral model version 2 (bmv2)"},{"key":"ref70","year":"2023","journal-title":"An Instant Virtual Network on Your Laptop"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/NETSOFT.2019.8806649"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1402946.1402967"},{"key":"ref68","author":"krizhevsky","year":"2023","journal-title":"Cifar-100 (canadian institute for advanced research)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2582748"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref26","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","author":"xiao","year":"2018","journal-title":"Proc 5th USENIX Conf Operating Syst Design Implementation"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787507"},{"key":"ref69","year":"2022","journal-title":"The Wikitext Long Term Dependency Language Modeling Dataset"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref63","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2000.832225"},{"key":"ref66","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"arXiv 1409 1556"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322259"},{"key":"ref65","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"szegedy","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref27","article-title":"Communication-efficient distributed deep learning: A comprehensive survey","author":"tang","year":"2020","journal-title":"arXiv 2003 06307"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053834"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472900"},{"key":"ref62","year":"2022","journal-title":"Intel P4 Studio SDE"},{"key":"ref61","year":"2022","journal-title":"Iftop(8)"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/10286433\/10050420.pdf?arnumber=10050420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T20:03:05Z","timestamp":1699300985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10050420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":75,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2023.3244794","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}