{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:12:16Z","timestamp":1785420736185,"version":"3.56.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2031"],"award-info":[{"award-number":["U22B2031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61932016"],"award-info":[{"award-number":["61932016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132011"],"award-info":[{"award-number":["62132011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202258"],"award-info":[{"award-number":["62202258"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation for Distinguished Young Scholars of China","award":["61825204"],"award-info":[{"award-number":["61825204"]}]},{"name":"Beijing Outstanding Young Scientist Program","award":["BJJWZYJH01201910003011"],"award-info":[{"award-number":["BJJWZYJH01201910003011"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M701894"],"award-info":[{"award-number":["2021M701894"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China National Postdoctoral Program for Innovative Talents, Shuimu Tsinghua Scholar Program"},{"name":"Ant Group through the CCF-Ant Innovative Research Program","award":["CCF-AFSGRF20210023"],"award-info":[{"award-number":["CCF-AFSGRF20210023"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tnet.2023.3328632","type":"journal-article","created":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T19:06:57Z","timestamp":1702408017000},"page":"1873-1887","source":"Crossref","is-referenced-by-count":19,"title":["FedPAGE: Pruning Adaptively Toward Global Efficiency of Heterogeneous Federated Learning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6133-7434","authenticated-orcid":false,"given":"Guangmeng","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8776-8730","authenticated-orcid":false,"given":"Qi","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Network Sciences and Cyberspace, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3632-3381","authenticated-orcid":false,"given":"Yi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9316-4578","authenticated-orcid":false,"given":"Qi","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5165-2787","authenticated-orcid":false,"given":"Su","family":"Yao","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-8517","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. AISTATS","author":"McMahan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"ref3","first-page":"1","article-title":"Improving mapreduce performance in heterogeneous environments","volume-title":"Proc. USENIX OSDI","author":"Zaharia"},{"key":"ref4","first-page":"185","article-title":"Effective straggler mitigation: Attack of the clones","volume-title":"Proc. USENIX NSDI","author":"Ananthanarayanan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586241"},{"key":"ref6","first-page":"1","article-title":"HeteroFL: Computation and communication efficient federated learning for heterogeneous clients","volume-title":"Proc. ICLR","author":"Diao"},{"key":"ref7","first-page":"1","article-title":"Efficient split-mix federated learning for on-demand and in-situ customization","volume-title":"Proc. ICLR","author":"Hong"},{"key":"ref8","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016","journal-title":"arXiv:1607.03250"},{"key":"ref9","first-page":"2133","article-title":"Gate decorator: Global filter pruning method for accelerating deep convolutional neural networks","volume-title":"Proc. NIPS","author":"You"},{"key":"ref10","first-page":"9356","article-title":"DropNet: Reducing neural network complexity via iterative pruning","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900130"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17301"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3213358"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20903"},{"key":"ref16","first-page":"8253","article-title":"FetchSGD: Communication-efficient federated learning with sketching","volume-title":"Proc. ACM ICML","author":"Rothchild"},{"key":"ref17","first-page":"12878","article-title":"Data-free knowledge distillation for heterogeneous federated learning","volume-title":"Proc. ICML","author":"Zhu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11709"},{"key":"ref19","first-page":"1","article-title":"DARTS-: Robustly stepping out of performance collapse without indicators","volume-title":"Proc. ICLR","author":"Chu"},{"key":"ref20","first-page":"1","article-title":"Faster CNNs with direct sparse convolutions and guided pruning","volume-title":"Proc. ICLR","author":"Park"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref22","first-page":"1","article-title":"Pruning filters for efficient ConvNets","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00290"},{"key":"ref27","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. NIPS","author":"Han"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00159"},{"key":"ref29","first-page":"1","article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"Proc. ICLR","author":"Molchanov"},{"key":"ref30","first-page":"5544","article-title":"Soft threshold weight reparameterization for learnable sparsity","volume-title":"Proc. ACM ICML","author":"Kusupati"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3035770"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3223234"},{"key":"ref33","first-page":"1508","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","volume-title":"Proc. NIPS","author":"Wen"},{"key":"ref34","first-page":"629","article-title":"GAIA: Geo-distributed machine learning approaching LAN speeds","volume-title":"Proc. USENIX NDSI)","author":"Hsieh"},{"key":"ref35","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Konecny","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref36","first-page":"1","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proc. ICLR","author":"Lin"},{"key":"ref37","article-title":"Expanding the reach of federated learning by reducing client resource requirements","author":"Caldas","year":"2018","journal-title":"arXiv:1812.07210"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref39","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","author":"Li"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356156"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9195"},{"key":"ref42","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. NIPS","author":"Ho"},{"key":"ref43","first-page":"1","article-title":"Learning efficient parameter server synchronization policies for distributed SGD","volume-title":"Proc. ICLR","author":"Zhu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3166101"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS51825.2021.9484526"},{"key":"ref46","first-page":"3597","article-title":"Deconstructing lottery tickets: Zeros, signs, and the supermask","volume-title":"Proc. NIPS","author":"Zhou"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"ref48","article-title":"Federated learning for mobile keyboard prediction","author":"Hard","year":"2018","journal-title":"arXiv:1811.03604"},{"key":"ref49","volume-title":"Numerical Analysis","author":"Sauer","year":"2006"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6424"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref52","first-page":"1","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796818"},{"key":"ref54","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref57","article-title":"Asynchronous federated optimization","author":"Xie","year":"2019","journal-title":"arXiv:1903.03934"},{"key":"ref58","first-page":"1","article-title":"Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers","volume-title":"Proc. ICLR","author":"Ye"},{"key":"ref59","first-page":"14037","article-title":"Are sixteen heads really better than one?","volume-title":"Proc. NIPS","author":"Michel"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref61","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. ACM ICML","author":"Karimireddy"},{"key":"ref62","first-page":"1","article-title":"An agnostic approach to federated learning with class imbalance","volume-title":"Proc. ICLR","author":"Shen"},{"key":"ref63","first-page":"1","article-title":"Toward understanding the impact of staleness in distributed machine learning","volume-title":"Proc. ICLR","author":"Dai"},{"key":"ref64","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","volume-title":"Proc. ACM ICML","author":"Yurochkin"},{"key":"ref65","first-page":"1","article-title":"Federated learning based on dynamic regularization","volume-title":"Proc. ICLR","author":"Acar"},{"key":"ref66","first-page":"1","article-title":"Hybrid local SGD for federated learning with heterogeneous communications","volume-title":"Proc. ICLR","author":"Guo"},{"key":"ref67","first-page":"1","article-title":"Federated adversarial domain adaptation","volume-title":"Proc. ICLR","author":"Peng"},{"key":"ref68","article-title":"LEAF: A benchmark for federated settings","author":"Caldas","year":"2018","journal-title":"arXiv:1812.01097"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/34.291440"},{"key":"ref72","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. ICML","author":"Ganin"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/10559910\/10355680.pdf?arnumber=10355680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T04:37:04Z","timestamp":1725338224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10355680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":72,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2023.3328632","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}