{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T02:31:12Z","timestamp":1775788272714,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":"crossref","award":["62372426"],"award-info":[{"award-number":["62372426"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["62132019"],"award-info":[{"award-number":["62132019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["62102392"],"award-info":[{"award-number":["62102392"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Science Foundation of Jiangsu Province","award":["BK20210121"],"award-info":[{"award-number":["BK20210121"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovation Promotion Association of the Chinese Academy of Science","award":["2023481"],"award-info":[{"award-number":["2023481"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tnet.2024.3414853","type":"journal-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T17:50:38Z","timestamp":1718905838000},"page":"4317-4332","source":"Crossref","is-referenced-by-count":18,"title":["PARING: Joint Task Placement and Routing for Distributed Training With In-Network Aggregation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3391-5118","authenticated-orcid":false,"given":"Yuhang","family":"Qiu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"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, Anhui, China"}]},{"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, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2768-6607","authenticated-orcid":false,"given":"He","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4679-6572","authenticated-orcid":false,"given":"Chunming","family":"Qiao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3285029"},{"key":"ref3","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"Lin","year":"2017","journal-title":"arXiv:1712.01887"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref5","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. 25th Int. Conf. Neural Inf. Process. Syst.","volume":"1","author":"Dean"},{"key":"ref6","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Jiang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3187009.3177734"},{"key":"ref8","article-title":"Scaling distributed machine learning with in-network aggregation","author":"Sapio","year":"2019","journal-title":"arXiv:1903.06701"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"ref11","first-page":"829","article-title":"In-network aggregation for shared machine learning clusters","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Gebara"},{"key":"ref12","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","volume-title":"Proc. 18th USENIX Symp. Networked Syst. Design Implement. (NSDI)","author":"Lao"},{"key":"ref13","first-page":"279","article-title":"Accelerating distributed reinforcement learning with in-switch computing","volume-title":"Proc. ACM\/IEEE 46th Annu. Int. Symp. Comput. Archit. (ISCA)","author":"Li"},{"key":"ref14","volume-title":"Intel Tofino","year":"2021"},{"key":"ref15","volume-title":"32-Port Programmable Switch","year":"2022"},{"key":"ref16","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","volume":"1","author":"Li"},{"key":"ref17","article-title":"Alpa: Automating inter- and intra-operator parallelism for distributed deep learning","author":"Zheng","year":"2022","journal-title":"arXiv:2201.12023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3457913.3457936"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2018.00028"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2999572.2999588"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3244794"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00453-001-0038-2"},{"key":"ref24","first-page":"323","article-title":"A nearly best-possible approximation for node-weighted Steiner trees","volume-title":"Proc. 3rd MPS Conf. Integer. Program. Combination Optim.","author":"Klein"},{"key":"ref25","volume-title":"Combinatorial Optimization","author":"Cook","year":"1998"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00054"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3485983.3494853"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.107.2100635"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1402946.1402967"},{"issue":"2","key":"ref32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3377454","article-title":"A survey on distributed machine learning","volume":"53","author":"Verbraeken","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref35","first-page":"577","article-title":"Enabling wide-spread communications on optical fabric with MegaSwitch","volume-title":"Proc. 14th USENIX Symp. Networked Syst. Design Implement. (NSDI)","author":"Chen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3406221"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098838"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2716281.2836126"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472900"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294915"},{"key":"ref41","first-page":"418","article-title":"TicTac: Accelerating distributed deep learning with communication scheduling","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Hashemi"},{"key":"ref42","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00072"},{"key":"ref44","first-page":"5055","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"issue":"1","key":"ref45","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":"ref46","first-page":"1710","article-title":"QSGD: Communication-efficient SGD via randomized quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"3","author":"Alistarh"},{"key":"ref47","first-page":"53","article-title":"3LC: Lightweight and effective traffic compression for distributed machine learning","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Lim"},{"key":"ref48","first-page":"132","article-title":"Priority-based parameter propagation for distributed DNN training","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Jayarajan"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155282"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2947013"},{"key":"ref51","first-page":"172","article-title":"Blink: Fast and generic collectives for distributed ml","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Wang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486340"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2674005.2674996"},{"key":"ref54","first-page":"29","article-title":"Camdoop: Exploiting in-network aggregation for big data applications","volume-title":"Proc. 9th USENIX Symp. Networked Syst. Design Implement. (NSDI)","author":"Costa"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"ref56","volume-title":"NVIDIA Mellanox","year":"2022"},{"key":"ref57","volume-title":"NetFPGA","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3387948"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/90\/10720541\/10565927.pdf?arnumber=10565927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T04:37:10Z","timestamp":1729226230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10565927\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":58,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2024.3414853","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}