Blockchain Assisted Federated Learning over Wireless Channels: Dynamic Resource Allocation and Client Scheduling

TL;DR

This paper introduces a blockchain-assisted federated learning framework that enhances security by integrating training and mining at clients, and proposes a dynamic resource allocation algorithm to optimize training data size and energy use over wireless channels.

Contribution

It presents a novel BFL framework with client-side training and mining, and develops a Lyapunov-based optimization algorithm for resource allocation and client scheduling.

Findings

The DRACS algorithm improves learning accuracy over benchmarks.

It balances training data size and energy consumption effectively.

Experimental results validate the proposed method's efficiency.

Abstract

The blockchain technology has been extensively studied to enable distributed and tamper-proof data processing in federated learning (FL). Most existing blockchain assisted FL (BFL) frameworks have employed a third-party blockchain network to decentralize the model aggregation process. However, decentralized model aggregation is vulnerable to pooling and collusion attacks from the third-party blockchain network. Driven by this issue, we propose a novel BFL framework that features the integration of training and mining at the client side. To optimize the learning performance of FL, we propose to maximize the long-term time average (LTA) training data size under a constraint of LTA energy consumption. To this end, we formulate a joint optimization problem of training client selection and resource allocation (i.e., the transmit power and computation frequency at the client side), and solve the long-term mixed integer non-linear programming based on a Lyapunov technique. In particular, the proposed dynamic resource allocation and client scheduling (DRACS) algorithm can achieve a trade-off of [$\mathcal{O}(1/V)$, $\mathcal{O}(\sqrt{V})$] to balance the maximization of the LTA training data size and the minimization of the LTA energy consumption with a control parameter $V$. Our experimental results show that the proposed DRACS algorithm achieves better learning accuracy than benchmark client scheduling strategies with limited time or energy consumption.