解决延迟客户端在去中心化联邦学习中适应慢、通信成本高的问题。
On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach
- 用聚类压缩模型为代表中心点，大幅降低通信开销。
- 延迟客户端通过结构距离度量与同伴知识对齐，加速适应。
- 在多个数据集上实现最优性能，通信量减少超86%。
去中心化联邦学习（DFL）在异步环境中面临延迟客户端适应缓慢和通信成本高的问题，严重制约整体性能。为此，我们提出DFedCAD框架，通过中心点对齐的蒸馏实现快速适应。该方法首先采用加权聚类剪枝（WCP）将模型压缩为代表性中心点，显著降低通信开销；随后利用新型结构距离度量与可微分k-means蒸馏模块，使延迟客户端能智能地加权并对齐同伴知识，实现高效端到端知识迁移。在CIFAR-10、CIFAR-100和Tiny-ImageNet上的大量实验表明，DFedCAD在所有测试设置下均达到当前最优性能，同时通信开销降低超过86%。该框架为动态现实场景中的高效去中心化学习提供了可扩展且实用的解决方案。
原文摘要 · Abstract (English)
Decentralized Federated Learning (DFL) struggles with the slow adaptation of late-joining delayed clients and high communication costs in asynchronous environments. These limitations significantly hinder overall performance. To address this, we propose DFedCAD, a novel framework for rapid adaptation via Centroid-Aligned Distillation. DFedCAD first employs Weighted Cluster Pruning (WCP) to compress models into representative centroids, drastically reducing communication overhead. It then enables delayed clients to intelligently weigh and align with peer knowledge using a novel structural distance metric and a differentiable k-means distillation module, facilitating efficient end-to-end knowledge transfer. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet show that DFedCAD consistently achieves state-of-the-art performance, attaining the highest accuracy across all evaluated settings while reducing communication overhead by over 86%. Our framework provides a scalable and practical solution for efficient decentralized learning in dynamic, real-world scenarios.
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。