智能采样：借助友好邻居助力去中心化联邦学习
Smart Sampling: Helping from Friendly Neighbors for Decentralized Federated Learning
AI总结：
本文提出AFIND+算法，通过识别有益邻居、自适应调整采样数量并按其贡献聚合模型，在去中心化联邦学习中提升客户端性能，实验表明其优于现有采样算法且兼容主流DFL优化算法。
摘要：
联邦学习（FL）因其能够在保护隐私和降低通信成本的同时共享知识而受到广泛关注。与集中式联邦学习不同，去中心化联邦学习（DFL）采用一种无需中央服务器的网络架构，允许客户端之间直接通信，从而显著节省通信资源。然而，由于数据异质性，并非所有相邻节点都有助于提升本地客户端的模型性能。本文提出AFIND+，一种简单而高效的DFL邻居采样与聚合算法，旨在利用协作提升客户端模型性能。AFIND+能够识别有益的邻居，自适应调整所选邻居的数量，并根据邻居的贡献策略性地聚合其模型。在具有多样化数据划分的真实世界数据集上的数值结果表明，AFIND+优于DFL中的其他采样算法，并且与大多数现有DFL优化算法兼容。
英文摘要：
Federated Learning (FL) is gaining widespread interest for its ability to share knowledge while preserving privacy and reducing communication costs. Unlike Centralized FL, Decentralized FL (DFL) employs a network architecture that eliminates the need for a central server, allowing direct communication among clients and leading to significant communication resource savings. However, due to data heterogeneity, not all neighboring nodes contribute to enhancing the local client's model performance. In this work, we introduce \textbf{\emph{AFIND+}}, a simple yet efficient algorithm for sampling and aggregating neighbors in DFL, with the aim of leveraging collaboration to improve clients' model performance. AFIND+ identifies helpful neighbors, adaptively adjusts the number of selected neighbors, and strategically aggregates the sampled neighbors' models based on their contributions. Numerical results on real-world datasets with diverse data partitions demonstrate that AFIND+ outperforms other sampling algorithms in DFL and is compatible with most existing DFL optimization algorithms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
