Local Ai
RIPPLE in Still Water: Zero-Shot Clustering in Federated Learning with Wavelet Scattering Transform
arXiv:2610.03054v1 Announce Type: new Abstract: Clustered Federated Learning (FL) partitions a client population into groups of similar local distributions and trains one specialized model per cluster
arXiv:2610.03054v1 Announce Type: new Abstract: 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.
Related
- COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication
- EnCAgg: Enhanced Clustering Aggregation for Robust Federated Learning against Dynamic Model Poisoning
- Federated Soft Clustering via Generalized Total Variation Minimization
- Discovering Collaboration from Novelty: Random Network Distillation for Clustered Federated Learning
Source: arXiv cs.LG | 2026-10-05