DAG-AFL:Directed Acyclic Graph-based Asynchronous Federated Learning
This addresses asynchronous client participation and data heterogeneity in federated learning for resource-limited wireless devices, representing an incremental improvement over existing blockchain-based methods.
The paper tackled the challenges of resource consumption and inefficiency in blockchain-based federated learning by proposing DAG-AFL, which improved training efficiency by 22.7% and model accuracy by 6.5% on average compared to eight state-of-the-art approaches.
Due to the distributed nature of federated learning (FL), the vulnerability of the global model and the need for coordination among many client devices pose significant challenges. As a promising decentralized, scalable and secure solution, blockchain-based FL methods have attracted widespread attention in recent years. However, traditional consensus mechanisms designed for Proof of Work (PoW) similar to blockchain incur substantial resource consumption and compromise the efficiency of FL, particularly when participating devices are wireless and resource-limited. To address asynchronous client participation and data heterogeneity in FL, while limiting the additional resource overhead introduced by blockchain, we propose the Directed Acyclic Graph-based Asynchronous Federated Learning (DAG-AFL) framework. We develop a tip selection algorithm that considers temporal freshness, node reachability and model accuracy, with a DAG-based trusted verification strategy. Extensive experiments on 3 benchmarking datasets against eight state-of-the-art approaches demonstrate that DAG-AFL significantly improves training efficiency and model accuracy by 22.7% and 6.5% on average, respectively.