Yangyang Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yangyang Wang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Dongxiao Yu
Shandong University
1 shared publication - Huashan Chen
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publication - Hui Xiong
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and The Hong Kong University of Science and Technology, Hong Kong SAR, China
1 shared publication - Mingyi Li
School of Computer Science and Technology, Shandong University, Qingdao, China
1 shared publication - Tian Lan
Beijing Institute of Technology
1 shared publication - Xiao Zhang
Shandong University
1 shared publication
Latest Publications
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2444-2455
Theoretical Convergence Guaranteed Resource-Adaptive Federated Learning with Mixed Heterogeneity
In this paper, we propose an adaptive learning paradigm for resource-constrained cross-device federated learning, in which heterogeneous local submodels with varying resources can be jointly trained to produce a global model. Different from existing studies, the submodel structures of different clients are formed by arbitrarily assigned neurons according to their local resources. Along this line, we first design a general resource-adaptive federated learning algorithm, namely RA-Fed, and rigorously prove its convergence with asymptotically optimal rate O(1/√Γ*TQ) under loose assumptions. Furthermore, to address both submodels heterogeneity and data heterogeneity challenges under non-uniform training, we come up with a new server aggregation mechanism RAM-Fed with the same theoretically proved convergence rate. Moreover, we shed light on several key factors impacting convergence, such as minimum coverage rate, data heterogeneity level, submodel induced noises. Finally, we conduct extensive experiments on two types of tasks with three widely used datasets under different experimental settings. Compared with the state-of-the-arts, our methods improve the accuracy up to 10% on average. Particularly, when submodels jointly train with 50% parameters, RAM-Fed achieves comparable accuracy to FedAvg trained with the full model.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2444-2455
Open AccessTheoretical Convergence Guaranteed Resource-Adaptive Federated Learning with Mixed Heterogeneity
In this paper, we propose an adaptive learning paradigm for resource-constrained cross-device federated learning, in which heterogeneous local submodels with varying resources can be jointly trained to produce a global model. Different from existing studies, the submodel structures of different clients are formed by arbitrarily assigned neurons according to their local resources. Along this line, we first design a general resource-adaptive federated learning algorithm, namely RA-Fed, and rigorously prove its convergence with asymptotically optimal rate O(1/√Γ*TQ) under loose assumptions. Furthermore, to address both submodels heterogeneity and data heterogeneity challenges under non-uniform training, we come up with a new server aggregation mechanism RAM-Fed with the same theoretically proved convergence rate. Moreover, we shed light on several key factors impacting convergence, such as minimum coverage rate, data heterogeneity level, submodel induced noises. Finally, we conduct extensive experiments on two types of tasks with three widely used datasets under different experimental settings. Compared with the state-of-the-arts, our methods improve the accuracy up to 10% on average. Particularly, when submodels jointly train with 50% parameters, RAM-Fed achieves comparable accuracy to FedAvg trained with the full model.