A Blockchain-Based Auditable Semi-Asynchronous Federated Learning for Heterogeneous Clients

Federated learning (FL) is a privacy-preserving approach in Artificial Intelligence (AI) that involves exchanging intermediate training parameters instead of raw data, thereby avoiding privacy breaches and promoting effective data collaboration. However, FL still faces several unresolved challenges, including trust issues among participants because traditional FL lacks a mutual consensus auditing mechanism. Another challenge is that when the number of participating nodes is large and resources are heterogeneous; this can lead to low efficiency. To overcome these challenges, we propose a Blockchain-based Auditable Semi-Asynchronous Federated Learning (BASA-FL) system. BASA-FL includes a smart contract that coordinates and records the FL exchange process, enabling the ability to trace and audit the behavior of participating workers. In addition, we proposed an efficient semi-asynchronous approach in blockchain-based distributed FL as the main contribution to addressing heterogeneous problems. We designed a method to quantify worker contributions and distribute rewards based on their contributions. We used a multi-index comprehensive evaluation to motivate workers to maintain high-quality and efficient participation in FL tasks. We conducted several simulations to evaluate the effectiveness of the semi-asynchronous mode, the reliability of the audit mechanism, and the contribution quantification strategy.