DAG-AFL:Directed Acyclic Graph-based Asynchronous Federated Learning

TL;DR

DAG-AFL introduces a blockchain-inspired asynchronous federated learning framework using directed acyclic graphs to enhance training efficiency and model accuracy while reducing resource consumption.

Contribution

The paper presents a novel DAG-based asynchronous federated learning framework that addresses client heterogeneity and resource constraints without heavy blockchain overhead.

Findings

Achieves 22.7% improvement in training efficiency

Attains 6.5% higher model accuracy

Outperforms eight state-of-the-art methods

Abstract

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.