{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T08:49:45Z","timestamp":1782895785642,"version":"3.54.5"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,25]]},"DOI":"10.1109\/ipdps65963.2026.00064","type":"proceedings-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:55:16Z","timestamp":1782852916000},"page":"693-706","source":"Crossref","is-referenced-by-count":0,"title":["MosaicUFL: A Fine-grained Unlabeled Client Selection Framework for Efficient Federated Learning"],"prefix":"10.1109","author":[{"given":"Nan","family":"Yang","sequence":"first","affiliation":[{"name":"The University of Sydney,Sydney,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zikang","family":"Wen","sequence":"additional","affiliation":[{"name":"The University of Sydney,Sydney,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuning","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Sydney,Sydney,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanli","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Sydney,Sydney,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaming","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Sydney,Sydney,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Yuan","sequence":"additional","affiliation":[{"name":"The University of Sydney,Sydney,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485946"},{"key":"ref2","article-title":"Towards federated learning at scale: System design","volume-title":"Proceedings of the 2nd MLSys Conference","author":"Bonawitz"},{"key":"ref3","article-title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","volume-title":"Proceedings of NeurIPS","volume":"30","author":"Alistarh"},{"key":"ref4","article-title":"FedML: A Research Library and Benchmark for Federated Machine Learning","volume-title":"NeurIPS Federated Learning Workshop","author":"He"},{"key":"ref5","article-title":"Gaia: Geo-distributed machine learning approaching LAN speeds","author":"Hsieh","year":"2017","journal-title":"USENIX NSDI"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483278"},{"key":"ref7","article-title":"Federated optimization in heterogeneous networks","author":"Li","year":"2020","journal-title":"MLSys"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485929"},{"key":"ref9","article-title":"Adaptive federated optimization","volume-title":"ICLR","author":"Reddi"},{"key":"ref10","first-page":"31","article-title":"Heteroswitch: Characterizing and taming system-induced data heterogeneity in federated learning","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Kim"},{"key":"ref11","first-page":"395","article-title":"Fedtrans: Efficient federated learning via multi-model transformation","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Zhu"},{"key":"ref12","first-page":"408","article-title":"Lifl: A lightweight, event-driven serverless platform for federated learning","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Qi"},{"key":"ref13","article-title":"Oort: Efficient federated learning via guided participant selection","author":"Lai","year":"2021","journal-title":"USENIX OSDI"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517017"},{"key":"ref15","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","author":"Sohn","year":"2020","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Mixmatch: A holistic approach to semi-supervised learning","author":"Berthelot","year":"2019","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Federated semi-supervised learning with inter-client consistency & disjoint learning","volume-title":"ICLR","author":"Jeong"},{"key":"ref18","article-title":"Bandit-based communication-efficient client selection strategies","author":"Cho","year":"2020","journal-title":"IEEE Asilomar"},{"key":"ref19","first-page":"21 811","article-title":"Client selection in federated learning: Principles, challenges, and opportunities","volume-title":"IEEE Internet of Things Journal","volume":"10","author":"Fu","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref21","article-title":"Semi-supervised learning of visual features","volume-title":"ICCV","author":"Assran"},{"key":"ref22","article-title":"Exponential moving average normalization","volume-title":"CVPR","author":"Cai"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.01485","article-title":"SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hu"},{"key":"ref24","article-title":"Pseudo-label : The simple and efficient semi-supervised learning method for deep neural networks","author":"Lee","year":"2013"},{"key":"ref25","article-title":"All labels are not created equal","volume-title":"CVPR","author":"Nassar"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01209"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01424"},{"key":"ref28","first-page":"9455","article-title":"Comatch: Semi-supervised learning with contrastive graph regularization","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Li"},{"key":"ref29","article-title":"Flexmatch: boosting semi-supervised learning with curriculum pseudo labeling","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Zhang"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.5244\/C.35.20","article-title":"Leveraging class hierarchies with metric-guided prototype learning","volume-title":"British Machine Vision Conference","author":"Garnot"},{"key":"ref31","first-page":"1214","article-title":"Improving semi-supervised federated learning by reducing the gradient diversity of models","volume-title":"2021 IEEE International Conference on Big Data (Big Data)","author":"Zhang"},{"key":"ref32","article-title":"Semifl: Semi-supervised federated learning for unlabeled clients with alternate training","volume-title":"Neural Information Processing Systems","author":"Diao","year":"2021"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.2172\/1525811","article-title":"On mixup training: Improved calibration and predictive uncertainty for deep neural networks","volume-title":"Neural Information Processing Systems","author":"Thulasidasan","year":"2019"},{"key":"ref34","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","volume-title":"ArXiv","volume":"abs\/2006.07733","author":"Grill","year":"2020"},{"key":"ref35","first-page":"205","article-title":"Enhancing the generalization of personalized federated learning with multi-head model and ensemble voting","volume-title":"2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","author":"Le"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS64566.2025.00053"},{"key":"ref37","first-page":"509","article-title":"Seafl: Enhancing efficiency in semi-asynchronous federated learning through adaptive aggregation and selective training","volume-title":"2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","author":"Islam"},{"key":"ref38","article-title":"Hugging face","author":"Face","year":"2023"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1145\/3477114.3488760","article-title":"Fedscale: Benchmarking model and system performance of federated learning at scale","volume-title":"International Conference on Machine Learning","author":"Lai"},{"key":"ref40","article-title":"Fedil: Federated incremental learning from decentralized unlabeled data with convergence analysis","volume-title":"ArXiv","author":"Yang","year":"2023"}],"event":{"name":"2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","location":"New Orleans, LA, USA","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11575315\/11575316\/11575416.pdf?arnumber=11575416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T08:39:08Z","timestamp":1782895148000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11575416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/ipdps65963.2026.00064","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}