静水涟漪：基于小波散射变换的联邦学习零样本聚类
RIPPLE in Still Water: Zero-Shot Clustering in Federated Learning with Wavelet Scattering Transform
浏览论文内容
中文总结 AI 辅助
RIPPLE提出一种联邦学习聚类框架，利用小波散射变换离线计算簇分配，实现零样本聚类，通信成本与FedAvg相当，并在多个基准上优于现有方法。
中文摘要 AI 辅助
聚类联邦学习（Clustered Federated Learning, FL）将客户端群体划分为具有相似本地分布的若干组，并为每个簇训练一个专门的模型，从而缓解在非独立同分布（non-IID）数据下导致单模型方法性能下降的客户端漂移问题。先前的方法在训练循环内部通过梯度相似性、损失评估或EM风格更新来发现簇结构，这增加了通信开销，使梯度暴露于反演攻击之下，并且无法为未参与训练的客户端分配簇。我们提出RIPPLE，一种聚类联邦学习框架，其中簇分配完全离线计算，基于每个客户端本地数据的谱特征：通过小波散射变换（Wavelet Scattering Transform）嵌入的方差加权主成分原型，并在联邦开始前由服务器端在合成客户端群体上训练的高斯混合变分自编码器（Gaussian Mixture VAE）进行解码。每轮通信成本与FedAvg完全一致，未参与训练的客户端仅需一次前向传播即可获得个性化模型，无需梯度计算、模型评估或额外的通信轮次。我们证明RIPPLE的替代聚类目标与理想目标之间的差距由一个可计算的量界定，该量随客户端样本量衰减且与联邦持续时间无关；每个簇的收敛速度达到非凸光滑目标的最小最大最优速率。在涵盖受控和现实异质性的五个基准测试中，RIPPLE始终优于所有基线，且在最具现实性的分区上优势更大。
英文摘要
Clustered Federated Learning (FL) partitions a client population into groups of similar local distributions and trains one specialized model per cluster, mitigating client drift that degrades single-model methods under non-IID data. Prior methods discover cluster structure inside the training loop through gradient similarity, loss evaluation, or EM-style updates, thus increasing communication overhead, exposing gradients to inversion attacks, and providing no mechanism to assign clients absent from training. We propose RIPPLE, a clustered FL framework in which cluster assignment is computed entirely offline from a spectral characterization of each client's local data: a variance-weighted principal-component prototype embedded via the Wavelet Scattering Transform and decoded by a Gaussian Mixture VAE trained server-side on synthetic client populations before federation begins. Per-round communication cost matches FedAvg exactly, and a client absent from training obtains a personalized model from a single forward pass, without gradient computation, model evaluation, or extra communication round. We prove that the gap between RIPPLE's surrogate clustered objective and the oracle is bounded by a computable quantity decaying with client sample size and independent of federation duration; per-cluster convergence matches the minimax-optimal rate for non-convex smooth objectives. Across five benchmarks spanning controlled and realistic heterogeneity, RIPPLE consistently outperforms all baselines, with margins growing on the most realistic partitions.
发表机构
- Politecnico di Torino（都灵理工大学）
机构由 AI 辅助整理，请以论文原文为准。
