Haikun Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Haikun Zheng has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Xingjian Lu
East China Normal University
2 shared publications - Yuhui Jiang
School of Computer Science and Technology, East China Normal University, Shanghai, China
2 shared publications - Hongyue Wu
Tianjin University
1 shared publication - Wei Mao
School of Computer Science and Technology, East China Normal University (ECNU), Shanghai, China
1 shared publication - Wenyan Liu
Ant Group, Hangzhou 310023, China
1 shared publication
Latest Publications
- 12 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 17 (2) , 617-630
POP-FL: Towards Efficient Federated Learning on Edge Using Parallel Over-Parameterization
Federated Learning (FL) is a promising paradigm for mining massive data while respecting users' privacy. However, the deployment of FL on resource-constrained edge devices remains elusive due to its high resource demand. In this paper, unlike existing works that use expensive dense models, we propose to utilize dynamic sparse training in FL and design a novel sparse-to-sparse FL framework, named as POP-FL. The framework can reduce both computation and communication overheads while maintaining the performance of the global model. Specifically, POP-FL partitions massive clients into groups and performs parallel parameter exploration, i.e., Parallel Over-Parameterization , over the collaboration between these groups. This exploration can greatly improve the expressibility and generalizability of sparse training in FL (especially for extreme sparsity levels) through reliably covering sufficient parameters and dynamically updating the global sparse network's structure during the training process. Experimental results show that compared with existing sparse-to-sparse training methods in both iid and non-iid data distribution, POP-FL achieves the best inference accuracy on various representative networks.
- 12 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 17 (2) , 617-630
POP-FL: Towards Efficient Federated Learning on Edge Using Parallel Over-Parameterization
Federated Learning (FL) is a promising paradigm for mining massive data while respecting users' privacy. However, the deployment of FL on resource-constrained edge devices remains elusive due to its high resource demand. In this paper, unlike existing works that use expensive dense models, we propose to utilize dynamic sparse training in FL and design a novel sparse-to-sparse FL framework, named as POP-FL. The framework can reduce both computation and communication overheads while maintaining the performance of the global model. Specifically, POP-FL partitions massive clients into groups and performs parallel parameter exploration, i.e., Parallel Over-Parameterization , over the collaboration between these groups. This exploration can greatly improve the expressibility and generalizability of sparse training in FL (especially for extreme sparsity levels) through reliably covering sufficient parameters and dynamically updating the global sparse network's structure during the training process. Experimental results show that compared with existing sparse-to-sparse training methods in both iid and non-iid data distribution, POP-FL achieves the best inference accuracy on various representative networks.
- Top Cited Papers
- 5 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 17 (1) , 336-348
Joint Client Selection and Bandwidth Allocation of Wireless Federated Learning by Deep Reinforcement Learning
Federated Learning (FL) is a promising paradigm for massive data mining service while protecting users' privacy. In wireless federated learning networks (WFLNs), limited communication resources and heterogeneity of user devices have essential impacts on training efficiency of FL, hence it is critical to select clients and allocate network bandwidths among them in each learning round to improve the training efficiency. In this paper, we formulate the joint client selection and bandwidth allocation optimization problem as a MDP process and design a FL framework CSBWA to solve it. CSBWA relies on DRL-based REINFORCE algorithm to automatically perform effective policy based on observed information, e.g. client states, historical bandwidths, and feedback rewards. It is able to achieve lower time cost and energy consumption with long-term FL performance guarantee by jointly optimizing the client selection and bandwidth allocation. Experimental results show the effectiveness of CSBWA in reducing time cost and energy consumption while guaranteeing model performance of wireless federated learning compared with existing state-of-art methods.
- 5 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 17 (1) , 336-348
Top Cited PapersJoint Client Selection and Bandwidth Allocation of Wireless Federated Learning by Deep Reinforcement Learning
Federated Learning (FL) is a promising paradigm for massive data mining service while protecting users' privacy. In wireless federated learning networks (WFLNs), limited communication resources and heterogeneity of user devices have essential impacts on training efficiency of FL, hence it is critical to select clients and allocate network bandwidths among them in each learning round to improve the training efficiency. In this paper, we formulate the joint client selection and bandwidth allocation optimization problem as a MDP process and design a FL framework CSBWA to solve it. CSBWA relies on DRL-based REINFORCE algorithm to automatically perform effective policy based on observed information, e.g. client states, historical bandwidths, and feedback rewards. It is able to achieve lower time cost and energy consumption with long-term FL performance guarantee by jointly optimizing the client selection and bandwidth allocation. Experimental results show the effectiveness of CSBWA in reducing time cost and energy consumption while guaranteeing model performance of wireless federated learning compared with existing state-of-art methods.