Context-Aware Consensus Algorithm for Blockchain-Empowered Federated Learning

Yao Zhao

doi:10.1109/TCC.2024.3372814

2024-04-01

PRE

Yao Zhao

Youyang Qu

Yong Xiang (Yong Xiang)

Feifei Chen

Longxiang Gao *

DOI：10.1109/TCC.2024.3372814

原文链接

原文求助

摘要

En 中文

Supported by cloud computing, Federated Learning (FL) has experienced rapid advancement, as a promising technique to motivate clients to collaboratively train models without sharing local data. To improve the security and fairness of FL implementation, numerous Blockchain-empowered Federated Learning (BFL) frameworks have emerged accordingly. Among them, consensus algorithms play a pivotal role in determining the scalability, security, and consistency of BFL systems. Existing consensus solutions to block producer selection and reward allocation either focus on well-resourced scenarios or accommodate BFL based on clients' contributions to model training. However, these approaches limit consensus efficiency and undermine reward fairness, due to involving intricate consensus processes, disregarding clients' contributions during blockchain consensus, and failing to address lazy client problems (malicious clients plagiarizing local model updates from others to reap rewards). Given the aforementioned challenges, we make the first attempt to design a joint solution for efficient consensus and fair reward allocation in heterogeneous BFL systems with lazy clients. Specifically, we introduce a generalizable BFL workflow that can address lazy client problems well. Based on it, the global contribution of BFL clients is decoupled into five dominant metrics, and the block producer selection problem is formulated as a reward-constraint contribution maximization problem. By addressing this problem, the optimal block producer that maximizes global contribution can be identified to orchestrate consensus processes, and rewards are distributed to clients in proportion to their respective global contributions. To achieve it, we develop a Context-aware Proof-of-Contribution consensus algorithm named CPoC to reach consensus and incentive simultaneously, followed by theoretical analysis of lazy client problems and privacy issues. Empirical results on widely-used datasets demonstrate the effectiveness of our design in improving consensus efficiency and maximizing global contribution.

Keyword:

Training

Blockchains

Delays

Computational modeling

Consensus algorithm

Federated learning

Cloud computing

blockchain

federated learning

lazy client

incentive mechanism