{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T05:20:29Z","timestamp":1773033629993,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825396","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"8052-8061","source":"Crossref","is-referenced-by-count":1,"title":["Revisiting System-Heterogeneous Federated Learning through Dynamic Model Search"],"prefix":"10.1109","author":[{"given":"Dixi","family":"Yao","sequence":"first","affiliation":[{"name":"University of Toronto, Hemlig AI"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th International Conference on Artificial Intelligence and Statistics (AISTATS)","volume":"54","author":"McMahan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483278"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3046250"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482107"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SEC50012.2020.00060"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3494981"},{"key":"ref8","article-title":"Federated learning based on dynamic regularization","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Acar"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00084"},{"key":"ref10","article-title":"FedNAS: Federated deep learning via neural architecture search","volume-title":"CVPR 2020 Workshop on Neural Architecture Search and Beyond for Representation Learning","author":"He"},{"key":"ref11","article-title":"Direct federated neural architecture search","volume-title":"ICLR 2021 Workshop on Distributed and Private Machine Learning (DPML)","author":"Garg"},{"key":"ref12","article-title":"Cross-device federated architecture search","volume-title":"Workshop on Federated Learning: Recent Advances and New Challenges (in Conjunction with NeurIPS 2022)","author":"Laskaridis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29576"},{"key":"ref14","article-title":"FjORD: Fair and accurate federated learning under heterogeneous targets with ordered dropout","volume-title":"Proc. Advances in Neural Information Processing Systems 34 (NeurIPS)","author":"Horvath"},{"key":"ref15","article-title":"HeteroFL: Computation and communication efficient federated learning for heterogeneous clients","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Diao"},{"key":"ref16","article-title":"FedRolex: Model-heterogeneous federated learning with rolling sub-model extraction","volume-title":"Proc. Advances in Neural Information Processing Systems 36 (NeurIPS)","author":"Alam"},{"key":"ref17","article-title":"Expanding the reach of federated learning by reducing client resource requirements","author":"Caldas","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229017"},{"key":"ref19","article-title":"Mistify: Automating dnn model porting for on-device inference at the edge","volume-title":"Proc. USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Guo"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00101"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419215"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3510831"},{"key":"ref23","article-title":"Distilling the knowledge in a neural network","volume-title":"NIPS Deep Learning and Representation Learning Workshop","author":"Hinton"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3227403"},{"key":"ref26","article-title":"Efficient Split-Mix federated learning for on-demand and in-situ customization","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Hong"},{"key":"ref27","first-page":"6630","article-title":"Efficient and light-weight federated learning via asynchronous distributed dropout","volume-title":"Proc. 26th International Conference on Artificial Intelligence and Statistics (AISTATS)","volume":"206","author":"Dun"},{"key":"ref28","article-title":"Learning multiple layers of features from tiny images","volume-title":"Master\u2019s thesis","author":"Krizhevsky","year":"2009"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"ref31","article-title":"Fedmd: Heterogenous federated learning via model distillation","author":"Li","year":"2019"},{"key":"ref32","article-title":"Ensemble distillation for robust model fusion in federated learning","volume-title":"Proc. Advances in Neural Information Processing Systems 33 (NeurIPS)","author":"Lin"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/399"},{"key":"ref34","first-page":"12 878","article-title":"Data-free knowledge distillation for heterogeneous federated learning","volume-title":"Proc. 38th International Conference on Machine Learning (ICML), ser. Proceedings of Machine Learning Research","volume":"139","author":"Zhu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3603165.3607364"},{"key":"ref37","article-title":"LEAF: A benchmark for federated settings","author":"Caldas","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Dosovitskiy"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2601087"},{"key":"ref42","article-title":"On the convergence of fedavg on non-iid data","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Li"},{"key":"ref43","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. 37th International Conference on Machine Learning (ICML)","volume":"119","author":"Karimireddy"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","location":"Washington, DC, USA","start":{"date-parts":[[2024,12,15]]},"end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825396.pdf?arnumber=10825396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:18:37Z","timestamp":1737101917000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825396\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825396","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}