{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:08:21Z","timestamp":1780765701155,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF1203001"],"award-info":[{"award-number":["2022YFF1203001"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172155, 62072465 and 62102425"],"award-info":[{"award-number":["62172155, 62072465 and 62102425"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Defence Science Organisation (DSO) National Laboratories under the AI Singapore Programme","award":["AISG2-RP-2020-019 and FCP-ASTAR-TG-2022-003"],"award-info":[{"award-number":["AISG2-RP-2020-019 and FCP-ASTAR-TG-2022-003"]}]},{"name":"Singapore Ministry of Education (MOE) Tier 1","award":["RG87\/22"],"award-info":[{"award-number":["RG87\/22"]}]},{"name":"the Science and Technology Innovation Program of Hunan Province","award":["2022RC3061 and 2023RC3027"],"award-info":[{"award-number":["2022RC3061 and 2023RC3027"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680715","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"11070-11079","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["One-shot-but-not-degraded Federated Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1449-3777","authenticated-orcid":false,"given":"Hui","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8203-8146","authenticated-orcid":false,"given":"Minrui","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6620-1898","authenticated-orcid":false,"given":"Tongqing","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2297-2622","authenticated-orcid":false,"given":"Xinyi","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8218-3490","authenticated-orcid":false,"given":"Jiawen","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5726-833X","authenticated-orcid":false,"given":"Zhiping","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2023.100742"},{"key":"e_1_3_2_1_2_1","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS)","volume":"36","author":"Babakniya Sara","year":"2024","unstructured":"Sara Babakniya, Zalan Fabian, Chaoyang He, Mahdi Soltanolkotabi, and Salman Avestimehr. 2024. A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 36."},{"key":"e_1_3_2_1_3_1","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS). 118--128","author":"Blanchard Peva","year":"2017","unstructured":"Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, and Julien Stainer. 2017. Machine learning with adversaries: Byzantine tolerant gradient descent. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS). 118--128."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612597"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01591"},{"key":"e_1_3_2_1_7_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR).","author":"Dai Rong","year":"2023","unstructured":"Rong Dai, Yonggang Zhang, Ang Li, Tongliang Liu, Xun Yang, and Bo Han. 2023. Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting. In Proc. of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. of International Conference on Machine Learning (ICML). PMLR, 2611--2620","author":"Dennis Don Kurian","year":"2021","unstructured":"Don Kurian Dennis, Tian Li, and Virginia Smith. 2021. Heterogeneity for the win: One-shot federated clustering. In Proc. of International Conference on Machine Learning (ICML). PMLR, 2611--2620."},{"key":"e_1_3_2_1_9_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR).","author":"Diao Yiqun","year":"2022","unstructured":"Yiqun Diao, Qinbin Li, and Bingsheng He. 2022. Towards addressing label skews in one-shot federated learning. In Proc. of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00408"},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research (JMLR), Vol. 23, 120 (2022), 1--39.","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"e_1_3_2_1_12_1","volume-title":"One-shot federated learning. arXiv preprint arXiv:1902.11175","author":"Guha Neel","year":"2019","unstructured":"Neel Guha, Ameet Talwalkar, and Virginia Smith. 2019. One-shot federated learning. arXiv preprint arXiv:1902.11175 (2019)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proc","author":"Guo Binbin","unstructured":"Binbin Guo, Yuan Mei, Danyang Xiao, and Weigang Wu. 2021. PFL-MoE: Personalized federated learning based on mixture of experts. In Proc. of APWeb-WAIM. Springer, 480--486."},{"key":"e_1_3_2_1_14_1","volume-title":"FastMoE: A Fast Mixture-of-Expert Training System. arXiv preprint arXiv:2103.13262","author":"He Jiaao","year":"2021","unstructured":"Jiaao He, Jiezhong Qiu, Aohan Zeng, Zhilin Yang, Jidong Zhai, and Jie Tang. 2021. FastMoE: A Fast Mixture-of-Expert Training System. arXiv preprint arXiv:2103.13262 (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR).","author":"Heinbaugh Clare Elizabeth","year":"2022","unstructured":"Clare Elizabeth Heinbaugh, Emilio Luz-Ricca, and Huajie Shao. 2022. Data-free one-shot federated learning under very high statistical heterogeneity. In Proc. of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548764"},{"key":"e_1_3_2_1_18_1","volume-title":"Adaptive mixtures of local experts. Neural computation","author":"Jacobs Robert A","year":"1991","unstructured":"Robert A Jacobs, Michael I Jordan, Steven J Nowlan, and Geoffrey E Hinton. 1991. Adaptive mixtures of local experts. Neural computation, Vol. 3, 1 (1991), 79--87."},{"key":"e_1_3_2_1_19_1","volume-title":"Proc. of International Conference on Machine Learning (ICML). PMLR, 5132--5143","author":"Karimireddy Sai Praneeth","year":"2020","unstructured":"Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank Reddi, Sebastian Stich, and Ananda Theertha Suresh. 2020. SCAFFOLD: Stochastic controlled averaging for federated learning. In Proc. of International Conference on Machine Learning (ICML). PMLR, 5132--5143."},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR).","author":"Lepikhin Dmitry","year":"2020","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2020. GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In Proc. of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/205"},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. of Machine learning and Systems","volume":"2","author":"Li Tian","year":"2020","unstructured":"Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. 2020. Federated optimization in heterogeneous networks. In Proc. of Machine learning and Systems, Vol. 2. 429--450."},{"key":"e_1_3_2_1_24_1","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS)","volume":"30","author":"Lian Xiangru","year":"2017","unstructured":"Xiangru Lian, Ce Zhang, Huan Zhang, Cho-Jui Hsieh, Wei Zhang, and Ji Liu. 2017. Can decentralized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient descent. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 30."},{"key":"e_1_3_2_1_25_1","volume-title":"Moe-LLaVA: Mixture of experts for large vision-language models. arXiv preprint arXiv:2401.15947","author":"Lin Bin","year":"2024","unstructured":"Bin Lin, Zhenyu Tang, Yang Ye, Jiaxi Cui, Bin Zhu, Peng Jin, Junwu Zhang, Munan Ning, and Li Yuan. 2024. Moe-LLaVA: Mixture of experts for large vision-language models. arXiv preprint arXiv:2401.15947 (2024)."},{"key":"e_1_3_2_1_26_1","first-page":"2351","article-title":"Ensemble distillation for robust model fusion in federated learning","volume":"33","author":"Lin Tao","year":"2020","unstructured":"Tao Lin, Lingjing Kong, Sebastian U Stich, and Martin Jaggi. 2020. Ensemble distillation for robust model fusion in federated learning. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 33. 2351--2363.","journal-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611984"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_1_29_1","volume-title":"Proc. of Artificial Intelligence and Statistics. PMLR, 1273--1282","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Proc. of Artificial Intelligence and Statistics. PMLR, 1273--1282."},{"key":"e_1_3_2_1_30_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR).","author":"Papernot Nicolas","year":"2016","unstructured":"Nicolas Papernot, Mart\u00edn Abadi, \u00dalfar Erlingsson, Ian Goodfellow, and Kunal Talwar. 2016. Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data. In Proc. of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_32_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR).","author":"Shazeer Noam","year":"2016","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2016. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In Proc. of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_33_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR).","author":"Shazeer Noam","year":"2016","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2016. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In Proc. of International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_34_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR). Computational and Biological Learning Society.","author":"Simonyan K","year":"2015","unstructured":"K Simonyan and A Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proc. of International Conference on Learning Representations (ICLR). Computational and Biological Learning Society."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191879"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.04.035"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01174"},{"key":"e_1_3_2_1_38_1","unstructured":"LLaMA-MoE Team. 2023. LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training. https:\/\/github.com\/pjlab-sys4nlp\/llama-moe"},{"key":"e_1_3_2_1_39_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_40_1","first-page":"1565","article-title":"FedSCR: Structure-based communication reduction for federated learning","volume":"32","author":"Wu Xueyu","year":"2020","unstructured":"Xueyu Wu, Xin Yao, and Cho-Li Wang. 2020. FedSCR: Structure-based communication reduction for federated learning. IEEE Transactions on Parallel and Distributed Systems (TPDS), Vol. 32, 7 (2020), 1565--1577.","journal-title":"IEEE Transactions on Parallel and Distributed Systems (TPDS)"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02250"},{"key":"e_1_3_2_1_42_1","volume-title":"One-Shot Federated Learning with Classifier-Guided Diffusion Models. arXiv preprint arXiv:2311.08870","author":"Yang Mingzhao","year":"2023","unstructured":"Mingzhao Yang, Shangchao Su, Bin Li, and Xiangyang Xue. 2023. One-Shot Federated Learning with Classifier-Guided Diffusion Models. arXiv preprint arXiv:2311.08870 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"FedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning. arXiv preprint arXiv:2402.01350","author":"Yi Liping","year":"2024","unstructured":"Liping Yi, Han Yu, Chao Ren, Heng Zhang, Gang Wang, Xiaoguang Liu, and Xiaoxiao Li. 2024. FedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning. arXiv preprint arXiv:2402.01350 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Proc. of International Conference on Machine Learning (ICML). PMLR, 5650--5659","author":"Yin Dong","year":"2018","unstructured":"Dong Yin, Yudong Chen, Ramchandran Kannan, and Peter Bartlett. 2018. Byzantine-robust distributed learning: Towards optimal statistical rates. In Proc. of International Conference on Machine Learning (ICML). PMLR, 5650--5659."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"e_1_3_2_1_46_1","volume-title":"Proc. of International Conference on Machine Learning (ICML). 7252--7261","author":"Yurochkin Mikhail","year":"2019","unstructured":"Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh, Kristjan Greenewald, Nghia Hoang, and Yasaman Khazaeni. 2019. Bayesian nonparametric federated learning of neural networks. In Proc. of International Conference on Machine Learning (ICML). 7252--7261."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3472504"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS55811.2022.00017"},{"key":"e_1_3_2_1_49_1","first-page":"21414","article-title":"Dense: Data-free one-shot federated learning","volume":"35","author":"Zhang Jie","year":"2022","unstructured":"Jie Zhang, Chen Chen, Bo Li, Lingjuan Lyu, Shuang Wu, Shouhong Ding, Chunhua Shen, and Chao Wu. 2022. Dense: Data-free one-shot federated learning. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 35. 21414--21428.","journal-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"e_1_3_2_1_51_1","volume-title":"Distilled one-shot federated learning. arXiv preprint arXiv:2009.07999","author":"Zhou Yanlin","year":"2020","unstructured":"Yanlin Zhou, George Pu, Xiyao Ma, Xiaolin Li, and Dapeng Wu. 2020. Distilled one-shot federated learning. arXiv preprint arXiv:2009.07999 (2020)."},{"key":"e_1_3_2_1_52_1","volume-title":"Proc. of International Conference on Machine Learning (ICML). PMLR, 12878--12889","author":"Zhu Zhuangdi","year":"2021","unstructured":"Zhuangdi Zhu, Junyuan Hong, and Jiayu Zhou. 2021. Data-free knowledge distillation for heterogeneous federated learning. In Proc. of International Conference on Machine Learning (ICML). PMLR, 12878--12889."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475182"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680715","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:24Z","timestamp":1750291584000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680715"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":53,"alternative-id":["10.1145\/3664647.3680715","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680715","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}