用有向无环图提升联邦学习效率，兼顾安全与资源节省。
DAG-AFL:Directed Acyclic Graph-based Asynchronous Federated Learning
- 基于有向无环图设计异步联邦学习框架，优化节点选择策略。
- 相比现有方法，训练效率提升22.7%，模型准确率提高6.5%。
- 适合资源受限的无线设备场景，尤其适用于高异构数据环境。
由于联邦学习（FL）的分布式特性，全局模型的脆弱性以及大量客户端设备间的协调需求带来了显著挑战。近年来，基于区块链的联邦学习因其去中心化、可扩展性和安全性受到广泛关注。然而，传统类工作量证明（PoW）的共识机制在资源消耗上代价高昂，严重影响了联邦学习的效率，尤其是在无线和资源受限的设备上。为解决异步客户端参与和数据异构性问题，同时控制区块链引入的额外开销，本文提出基于有向无环图的异步联邦学习（DAG-AFL）框架。设计了一种考虑时间新鲜度、节点可达性和模型准确性的尖点选择算法，并结合基于DAG的可信验证机制。在三个基准数据集上对八种先进方法进行对比实验，结果表明，DAG-AFL平均提升训练效率22.7%、模型准确率6.5%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。