R$^{2}$Fed: Resilient Reinforcement Federated Learning for Industrial Applications

Zhang, Weishan; Yu, Fei; Chen, Leiming; Zeng, Xingjie; Zhao, Hongwei; Tian, Yonglin; Wang, Fei-Yue; Li, Longfei; Li, Zengxiang

doi:10.1109/tii.2022.3222369

Cited by 13 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, while these efforts predominantly focus on IoT environment applications -such as device selection, resource optimization, and communication enhancement -they seldom address federated learning's model weight calculation challenges. Therefore, Zhang et al proposed the R 2 Fed framework [27], employing the DDPG reinforcement learning method for adaptive client weight calculation. Chen et al [28] also constructed a trustworthy federated learning platform based on reinforcement learning methods.…”

Section: Federated Reinforcement Learningmentioning

confidence: 99%

FedDRL: Trustworthy Federated Learning Model Fusion Method Based on Staged Reinforcement Learning

Chen,

Zhang,

Dong

et al. 2024

cai

View full text Add to dashboard Cite

Federated learning facilitates collaborative data analysis among multiple participants while preserving user privacy. However, conventional federated learning approaches, typically employing weighted average techniques for model fusion, confront two significant challenges: 1. The inclusion of malicious models in the fusion process can drastically undermine the accuracy of the aggregated global model. 2. Due to the heterogeneity problem of devices and data, the number of client samples does not determine the weight value of the model. To solve those challenges, we propose a trustworthy model fusion method based on reinforcement learning (FedDRL), which includes two stages. In the first stage, we propose a reliable client selection mechanism to exclude malicious models from the fusion process. In the second stage, we propose an adaptive model fusion method that dynamically assigns weights based on model quality to aggregate the best global models. Finally, we validate our approach against five distinct model fusion scenarios, demonstrating that our algorithm significantly enhanced reliability without compromising accuracy.

show abstract

Section: Federated Reinforcement Learningmentioning

confidence: 99%