[
    {
        "id": "osp-16959",
        "type": "article-journal",
        "title": "Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering",
        "author": [
            {
                "family": "Park",
                "given": "Haemin"
            },
            {
                "family": "Klabjan",
                "given": "Diego"
            },
            {
                "family": "Braun",
                "given": "Martin W."
            },
            {
                "family": "Li",
                "given": "Xiuqi"
            },
            {
                "family": "Ananthanarayanan",
                "given": "Balakrishnan"
            }
        ],
        "URL": "https://omanscience.com/en/articles/fed-brdecs-privacy-preserving-and-heterogeneity-aware-federated-deep-embedded-clustering",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]