.png){kind=icon}
返回
POP-FL: Towards Efficient Federated Learning on Edge Using Parallel Over-Parameterization
.png){kind=icon}
PRE
AI
DOI：10.1109/TSC.2024.3376194.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Training
Computational modeling
Data models
Servers
Adaptation models
Collaboration
Process control
Distributed machine learning
edge computing
federated learning
model sparse training
期刊
IF:
5.8
论文数:
2.2K
被引数:
6.5K
机构
引用论文
The Human Immunodeficiency Virus Type 1 Vpu Protein Enhances Membrane Permeability.png)
Biochemistry
BiochemistryIF0
PREAI
分享收藏Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing边缘智能: 用边缘计算铺平人工智能的最后一英里PROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAI分享收藏分享收藏Communication-Efficient Federated Learning for Wireless Edge Intelligence in IoT物联网中无线边缘智能的高效通信联合学习
PREAI
分享收藏Communication-Efficient Federated Learning With Compensated Overlap-FedAvg具有补偿重叠的交流高效联合学习-FedAvgOAAI
OAAI分享收藏
查看更多内容