通过拓扑信息对齐，提升非独立同分布下的联邦学习性能
FedTopo: Topology-Informed Representation Alignment in Federated Learning under Non-I.I.D. Conditions
- 用拓扑敏感块筛选机制选关键特征区域
- 在三个数据集上收敛更快，准确率超越现有方法
- 适合处理数据异构的视觉联邦学习任务
当前联邦学习模型在客户端数据异质（非独立同分布）时性能下降，因特征表示发散，像素或块级目标无法捕捉高维视觉任务所需的全局拓扑结构。本文提出 FedTopo 框架，结合拓扑引导块筛选（TGBS）与拓扑嵌入（TE），利用拓扑信息实现跨客户端表示的一致对齐。首先，TGBS 自动选择拓扑信息最丰富的块，即具有最大拓扑可分性的块，其基于持续性的签名能最好区分类内与类间样本对，确保后续分析聚焦于拓扑丰富特征。其次，该块生成紧凑的拓扑嵌入，量化每个客户端的拓扑信息。最后，拓扑对齐损失（TAL）在优化过程中引导客户端保持与全局模型的拓扑一致性，减少多轮迭代中的表示漂移。在 Fashion-MNIST、CIFAR-10 与 CIFAR-100 上，四种非独立同分布划分设置下实验表明，FedTopo 加速收敛并提升准确率，优于多个强基线。
原文摘要 · Abstract (English)
Current federated-learning models deteriorate under heterogeneous (non-I.I.D.) client data, as their feature representations diverge and pixel- or patch-level objectives fail to capture the global topology which is essential for high-dimensional visual tasks. We propose FedTopo, a framework that integrates Topological-Guided Block Screening (TGBS) and Topological Embedding (TE) to leverage topological information, yielding coherently aligned cross-client representations by Topological Alignment Loss (TAL). First, Topology-Guided Block Screening (TGBS) automatically selects the most topology-informative block, i.e., the one with maximal topological separability, whose persistence-based signatures best distinguish within- versus between-class pairs, ensuring that subsequent analysis focuses on topology-rich features. Next, this block yields a compact Topological Embedding, which quantifies the topological information for each client. Finally, a Topological Alignment Loss (TAL) guides clients to maintain topological consistency with the global model during optimization, reducing representation drift across rounds. Experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 under four non-I.I.D. partitions show that FedTopo accelerates convergence and improves accuracy over strong baselines.
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。