arXiv:2601. 06404v2 Announce Type: replace Abstract: Federated Clustering (FC) faces a critical bottleneck in real-world scenarios, i.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
The paper introduces Evolving Federated Density Peak Clustering (eFDPC), a one‑shot federated clustering method that merges evolving fuzzy data‑stream clustering with density peak clustering. Each client independently updates micro‑clusters from private mini‑batches, and only selected density peaks are sent to the server, reducing communication. A shuffler‑based anonymization layer protects client contributions, and two variants—eFDPC‑P and eFDPC‑G—are evaluated on synthetic and real datasets, outperforming recent federated clustering baselines in one‑shot settings and handling high‑dimensional, non‑IID data.
Fed-BRDECS is a federated deep embedded clustering framework that protects client privacy by replacing globally normalized clustering objectives with a locally computable sample‑stability loss, eliminating the need to share sensitive soft‑assignment distributions. It addresses non‑IID client data through prediction‑balanced sampling, which oversamples rare predicted clusters, and centroid‑level restarting, which refreshes biased or inactive centroids. Experiments on image, text, and time‑series datasets demonstrate that Fed‑BRDECS outperforms existing federated and deep clustering methods while adding no inference‑time cost for anomaly detection.
StoCFL is a clustered federated learning framework designed to address Non-IID data and dynamic client participation. It introduces a flexible clustering mechanism that allows arbitrary client participation and accommodates newly joined clients, improving data efficiency and model performance. Experiments on four Non-IID settings and a real-world dataset demonstrate that StoCFL achieves promising cluster results even when the number of clusters is unknown, outperforming baseline approaches across various scenarios.
RIPPLE is a clustered federated learning framework that assigns clients to groups based on an offline spectral characterization of their local data. It uses a variance‑weighted principal‑component prototype embedded via the Wavelet Scattering Transform and decoded by a Gaussian Mixture VAE trained on synthetic client populations. The method achieves the same per‑round communication cost as FedAvg, allows absent clients to receive a personalized model with a single forward pass, and demonstrates superior performance across five heterogeneous benchmarks.
arXiv:2303. 04345v2 Announce Type: replace Abstract: Federated learning (FL) is a promising framework that models distributed machine learning while protecting the privacy of clients.
ERIS is a federated learning framework that introduces Federated Shard Aggregation (FSA), partitioning client updates into shards aggregated by multiple client-side aggregators to eliminate a central bottleneck and limit data exposure. The framework can integrate Distributed Shifted Compression (DSC) to further reduce communication payloads and exposed coordinates. Experiments on image, text, and large language model tasks demonstrate that ERIS maintains FedAvg-level utility while significantly cutting communication overhead and enhancing robustness against membership inference and reconstruction attacks, all without heavy cryptography or utility‑degrading perturbations.