Joint Optimization for DAG-Blockchain-Assisted Federated Learning in Wireless Networks

In this article, an efficient wireless federated learning (FL) framework based on blockchain (BC) assistance is studied. Many existing frameworks adopt lots of third-party servers as consensus nodes, which is vulnerable to collusion attacks. In our framework, the blockchain-assisted FL (BFL) model selects edge users as blockchain nodes so that it does not need any third-party intervention. Besides, the convergence analysis of this FL algorithm considering transmission outages is provided to prove the effects of wireless factors on FL. To solve the low efficiency of the existing consensus process in the BFL, the Directed Acyclic Graph (DAG) blockchain is introduced into our work. Moreover, to achieve an excellent trade-off between FL performance and DAG-BC throughput, a joint optimization problem regarding DAG-BFL is formulated. To solve the complex nonconvex optimization problem, the joint communication and computing resource allocation as well as block designing schemes are proposed, which are based on the twin-loop penalty dual decomposition (PDD) method and the successive block minimization technique (BSUM). Numerical simulations are performed to demonstrate the effectiveness of the proposed method. Particularly, compared with the traditional alternative optimization (AO), the proposed PDD-based algorithm achieves better system performance.