Abstract
Federated deep clustering seeks to learn clustering-friendly representations from decentralized unlabeled data while preserving client privacy. However, Deep Embedded Clustering (DEC)-style objectives depend on global soft-assignment statistics that require clients to reveal their sensitive information. We propose Fed-BRDECS, a privacy-preserving and heterogeneity-aware federated deep embedded clustering framework. Fed-BRDECS replaces the globally normalized clustering objective with a locally computable sample-stability loss, avoiding the transmission of local soft-assignment distributions. To tackle non-IID client distributions, we introduce prediction-balanced sampling, which oversamples locally rare predicted clusters without requiring ground-truth labels, and centroid-level restarting, which periodically refreshes biased or inactive centroids. Experiments on image and text clustering benchmarks show that Fed-BRDECS consistently outperforms representative federated clustering and deep clustering baselines under both IID and non-IID partitions. We further demonstrate its applicability to federated time-series anomaly detection, where it improves reconstruction-based detectors without adding inference-time cost.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Park, H., Klabjan, D., Braun, M. W., Li, X., & Ananthanarayanan, B. (2026). Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering. https://omanscience.com/en/articles/fed-brdecs-privacy-preserving-and-heterogeneity-aware-federated-deep-embedded-clustering
MLA 9
Park, Haemin, et al. "Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering." https://omanscience.com/en/articles/fed-brdecs-privacy-preserving-and-heterogeneity-aware-federated-deep-embedded-clustering.
Chicago (author–date)
Park, Haemin, Diego Klabjan, Martin W. Braun, Xiuqi Li, and Balakrishnan Ananthanarayanan. 2026. "Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering." https://omanscience.com/en/articles/fed-brdecs-privacy-preserving-and-heterogeneity-aware-federated-deep-embedded-clustering.
Harvard
Park, H., Klabjan, D., Braun, M. W., Li, X. and Ananthanarayanan, B. (2026) 'Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering', Available at: https://omanscience.com/en/articles/fed-brdecs-privacy-preserving-and-heterogeneity-aware-federated-deep-embedded-clustering.
Vancouver
Park H, Klabjan D, Braun MW, Li X, Ananthanarayanan B. Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering. https://omanscience.com/en/articles/fed-brdecs-privacy-preserving-and-heterogeneity-aware-federated-deep-embedded-clustering
IEEE
H. Park, D. Klabjan, M. W. Braun, X. Li, and B. Ananthanarayanan, "Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering," https://omanscience.com/en/articles/fed-brdecs-privacy-preserving-and-heterogeneity-aware-federated-deep-embedded-clustering.