{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:38:12Z","timestamp":1773999492478,"version":"3.50.1"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010450","name":"Nova","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010450","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/globecom59602.2025.11432615","type":"proceedings-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:04:01Z","timestamp":1773950641000},"page":"1944-1949","source":"Crossref","is-referenced-by-count":0,"title":["Not All Gradients Are Equal: Dual Transport and Queue Dropping Strategy Guided by Spatiotemporal Gradient Importance"],"prefix":"10.1109","author":[{"given":"Zhichuan","family":"Zuo","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Lab of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Tian","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Lab of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeming","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Lab of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Lab of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Gong","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Lab of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wendong","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Lab of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3377454"},{"key":"ref2","article-title":"Bringing HPC techniques to deep learning","author":"Ring-Allreduce","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483553"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126456"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS57198.2023.10188699"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.03.006"},{"key":"ref8","article-title":"Which layer is learning faster? a systematic exploration of layer-wise convergence rate for deep neural networks","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chen"},{"key":"ref9","first-page":"1421","article-title":"Towards Domain-Specific network transport for distributed DNN training","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Wang"},{"key":"ref10","first-page":"14333","article-title":"Stochastic marginal likelihood gradients using neural tangent kernels","volume-title":"International Conference on Machine Learning","author":"Immer"},{"key":"ref11","first-page":"673","article-title":"Whale: Efficient giant model training over heterogeneous GPUs","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Jia"},{"key":"ref12","first-page":"1403","article-title":"CASSINI:Network-Aware Job Scheduling in Machine Learning Clusters","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Rajasekaran"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10000892"}],"event":{"name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","location":"Taipei, Taiwan","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["GLOBECOM 2025 - 2025 IEEE Global Communications Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11431620\/11431622\/11432615.pdf?arnumber=11432615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:07:28Z","timestamp":1773986848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11432615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/globecom59602.2025.11432615","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}