{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:33:56Z","timestamp":1778812436448,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1755850"],"award-info":[{"award-number":["1755850"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1841520"],"award-info":[{"award-number":["1841520"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2007716"],"award-info":[{"award-number":["2007716"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2007976"],"award-info":[{"award-number":["2007976"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1942594"],"award-info":[{"award-number":["1942594"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1907805"],"award-info":[{"award-number":["1907805"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jeffress Memorial Trust Award"},{"name":"Amazon Research Award"},{"DOI":"10.13039\/100007065","name":"NVIDIA Graphics Processing Unit","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Design Knowledge Company","award":["0827.002.120.04"],"award-info":[{"award-number":["0827.002.120.04"]}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62271371"],"award-info":[{"award-number":["62271371"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tnnls.2022.3223879","type":"journal-article","created":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T19:40:20Z","timestamp":1671478820000},"page":"4491-4501","source":"Crossref","is-referenced-by-count":3,"title":["Toward Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM Framework"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6635-4296","authenticated-orcid":false,"given":"Junxiang","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Informatics, Emory University, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyi","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Shaanxi, Xi\u2019an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Chai","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Virginia, Charlottesville, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0640-4140","authenticated-orcid":false,"given":"Yongchao","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Shaanxi, Xi\u2019an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1695-4864","authenticated-orcid":false,"given":"Yue","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Virginia, Charlottesville, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Informatics, Emory University, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kipf"},{"key":"ref2","article-title":"On graph neural networks versus graph-augmented mlps","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref3","article-title":"Understanding over-squashing and bottlenecks on graphs via curvature","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Topping"},{"key":"ref4","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref5","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref6","first-page":"2722","article-title":"Training neural networks without gradients: A scalable admm approach","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Taylor"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330936"},{"key":"ref8","first-page":"1509","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref9","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"Sergeev","year":"2018","journal-title":"arXiv:1802.05799"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807410"},{"key":"ref11","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015","journal-title":"arXiv:1512.01274"},{"key":"ref12","first-page":"418","article-title":"TicTac: Accelerating distributed deep learning with communication scheduling","volume-title":"Proc. 2nd SysML Conf.","author":"Hashemi"},{"key":"ref13","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","volume-title":"Proc. Annu. Tech. Conf. (USENIX ATC)","author":"Zhang"},{"key":"ref14","first-page":"2595","article-title":"Parallelized stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zinkevich"},{"key":"ref15","article-title":"Predict globally, correct locally: Parallel-in-time optimal control of neural networks","author":"Parpas","year":"2019","journal-title":"arXiv:1902.02542"},{"key":"ref16","first-page":"6659","article-title":"Training neural networks using features replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huo"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069883"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596796"},{"key":"ref20","article-title":"Gated graph sequence neural networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref21","first-page":"1106","article-title":"Learning steady-states of iterative algorithms over graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref22","article-title":"Spectral networks and locally connected networks on graphs","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Bruna"},{"key":"ref23","article-title":"Deep convolutional networks on graph-structured data","author":"Henaff","year":"2015","journal-title":"arXiv:1506.05163"},{"key":"ref24","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Defferrard"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10179"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939753"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/362"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04167-0_33"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom\/BigDataSE.2019.00096"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0024"},{"key":"ref32","volume-title":"Introduction to Algorithms","author":"Cormen","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00068"},{"key":"ref34","first-page":"208","article-title":"Alternating direction method of multipliers for quantization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Huang"},{"key":"ref35","volume-title":"Variational Analysis","volume":"317","author":"Rockafellar","year":"2009"},{"key":"ref36","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015","journal-title":"arXiv:1505.00853"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref38","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler","year":"2012","journal-title":"arXiv:1212.5701"},{"key":"ref39","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc.3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/10492491\/9992210-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10492491\/09992210.pdf?arnumber=9992210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:46:42Z","timestamp":1712692002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":40,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3223879","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}