解决异步联邦学习通信开销大、模型偏移问题，提升训练稳定性。
On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach
- 通过共享中心点空间实现通信、聚合与本地稳定一体化。
- 在非独立同分布数据下准确率最高提升6%，通信成本降低80%以上。
- 适合大规模异构系统，尤其适用于延迟参与和不规则通信场景。
异步去中心化联邦学习（ADFL）无需中心协调与全局同步，适用于大规模异构系统。但频繁的点对点通信、在有向拓扑上的异步更新以及非独立同分布（non-IID）数据共同导致过高的通信开销、聚合偏差和严重的模型漂移。我们提出PushCen-ADFL，一种通信高效的ADFL框架，可在通信不对称和客户端延迟参与条件下实现稳定训练。该方法将通信、聚合与本地稳定统一于共享中心点表示空间，形成压缩与优化之间的闭环。客户端交换中心点形式的消息，采用保持均值的推送求和混合策略纠正聚合偏差，并利用轻量级中心点正则化机制，在同一中心点空间内缓解异质性和延迟带来的漂移。此外，带有发送方去重的有界缓冲区进一步提升了在不规则异步到达下的鲁棒性。在视觉数据集上的实验表明，PushCen-ADFL在数据异构条件下准确率最高提升6%，同时每轮推送通信成本减少超过80%，实现了良好的准确率-通信权衡。
原文摘要 · Abstract (English)
Asynchronous decentralized federated learning (ADFL) eliminates central coordination and global synchronization, making it attractive for large-scale and heterogeneous systems. However, frequent peer-to-peer communication, asynchronous updates on directed topologies, and non-IID data jointly lead to excessive communication overhead, biased aggregation and severe model drift. We propose PushCen-ADFL, a communication-efficient ADFL framework that enables stable training under asymmetric communication and delayed client participation. PushCen-ADFL couples communication, aggregation, and local stabilization in a shared centroid representation space, forming a closed loop between compression and optimization. Clients exchange centroid-form messages, apply average-preserving push-sum mixing to correct aggregation bias, and use a lightweight centroid regularization anchored in the same centroid space to mitigate drift under heterogeneity and staleness. A bounded, sender-deduplicated buffer further improves robustness under irregular asynchronous arrivals. Experiments on vision datasets demonstrate that PushCen-ADFL improves accuracy under data heterogeneity by up to 6\% while reducing per-push communication cost by more than 80\%, achieving a favorable accuracy-communication trade-off.
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。