arXiv：cs.LG· Haemin Park, Diego Klabjan, Martin W. Braun, Xiuqi Li, Balakrishnan Ananthanarayanan·· 4 小时前AI 评分33
Fed-BRDECS：隐私保护且异构感知的联邦深度嵌入聚类
Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering
AI 导读
研究者提出 Fed-BRDECS，一个隐私保护且异构感知的联邦深度嵌入聚类框架，用本地可计算的样本稳定性损失替代全局归一化聚类目标，避免传输本地软分配分布。该方法引入预测均衡采样和质心级重启以应对非 IID 客户端分布，在图像与文本聚类基准上于 IID 和 non-IID 划分下均优于代表性联邦聚类与深度聚类基线，并可应用于联邦时间序列异常检测且不增加推理开销。
正文
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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.07399 [cs.LG] |
| (or arXiv:2610.07399v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07399 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haemin Park [view email]
[v1]
Mon, 5 Oct 2026 21:11:14 UTC (2,022 KB)
来源：arXiv：cs.LG · arxiv.org