FedRFQ: Prototype-Based Federated Learning with Reduced Redundancy, Minimal Failure, and Enhanced Quality
IEEE Transactions on Computers(2024)
摘要
Federated learning is a powerful technique that enables collaborative
learning among different clients. Prototype-based federated learning is a
specific approach that improves the performance of local models under non-IID
(non-Independently and Identically Distributed) settings by integrating class
prototypes. However, prototype-based federated learning faces several
challenges, such as prototype redundancy and prototype failure, which limit its
accuracy. It is also susceptible to poisoning attacks and server malfunctions,
which can degrade the prototype quality. To address these issues, we propose
FedRFQ, a prototype-based federated learning approach that aims to reduce
redundancy, minimize failures, and improve quality. FedRFQ
leverages a SoftPool mechanism, which effectively mitigates prototype
redundancy and prototype failure on non-IID data. Furthermore, we introduce the
BFT-detect, a BFT (Byzantine Fault Tolerance) detectable aggregation algorithm,
to ensure the security of FedRFQ against poisoning attacks and server
malfunctions. Finally, we conduct experiments on three different datasets,
namely MNIST, FEMNIST, and CIFAR-10, and the results demonstrate that FedRFQ
outperforms existing baselines in terms of accuracy when handling non-IID data.
更多查看译文
关键词
Federated Learning,SoftPool,Non-IID Data,Poisoning Attacks,Server Malfunction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要