A Federated Parallel Data Platform for Trustworthy AI

Chen, Leiming; Zhang, Weishan; Xu, Liang; Zeng, Xingjie; Lu, Qinghua; Zhao, Hongwei; Chen, Bingyang; Wang, Xiao

doi:10.1109/dtpi52967.2021.9540175

Cited by 2 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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%

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

show abstract

“…Trustworthy federated learning technology plays a pivotal role in safeguarding privacy and enabling collaborative learning for Trustworthy AI. To actualize Trustworthy AI, Chen et al [ 15 ] have devised a computational framework for trustworthy federated learning, ensuring the security of the entire federated learning process.…”

Section: Introductionmentioning

confidence: 99%

FedTKD: A Trustworthy Heterogeneous Federated Learning Based on Adaptive Knowledge Distillation

Chen,

Zhang,

Dong

et al. 2024

Entropy

Self Cite

View full text Add to dashboard Cite

Federated learning allows multiple parties to train models while jointly protecting user privacy. However, traditional federated learning requires each client to have the same model structure to fuse the global model. In real-world scenarios, each client may need to develop personalized models based on its environment, making it difficult to perform federated learning in a heterogeneous model environment. Some knowledge distillation methods address the problem of heterogeneous model fusion to some extent. However, these methods assume that each client is trustworthy. Some clients may produce malicious or low-quality knowledge, making it difficult to aggregate trustworthy knowledge in a heterogeneous environment. To address these challenges, we propose a trustworthy heterogeneous federated learning framework (FedTKD) to achieve client identification and trustworthy knowledge fusion. Firstly, we propose a malicious client identification method based on client logit features, which can exclude malicious information in fusing global logit. Then, we propose a selectivity knowledge fusion method to achieve high-quality global logit computation. Additionally, we propose an adaptive knowledge distillation method to improve the accuracy of knowledge transfer from the server side to the client side. Finally, we design different attack and data distribution scenarios to validate our method. The experiment shows that our method outperforms the baseline methods, showing stable performance in all attack scenarios and achieving an accuracy improvement of 2% to 3% in different data distributions.

show abstract

A Federated Parallel Data Platform for Trustworthy AI

Cited by 2 publications

References 7 publications

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

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

FedTKD: A Trustworthy Heterogeneous Federated Learning Based on Adaptive Knowledge Distillation

Contact Info

Product

Resources

About