Federated Deep Clustering Networks for High-Dimensional and Heterogeneous Data

Researchers introduced FedDCN, a generalization of Deep Clustering Networks to the federated scenario, detailed in arXiv paper 2609.21829v1. FedDCN simultaneously optimizes a reconstruction loss and a clustering loss, generating synthetic data augmentations and adding a geometric regularization for latent space alignment to remain robust under non-identically-independently distributed data across clients. Experimental evaluation demonstrated the approach's effectiveness under both IID and non-IID assumptions, and the authors identified future research directions.

arXiv:2609.21829v1 Announce Type: new Abstract: Clustering high-dimensional data is a fundamental task in unsupervised machine learning with applications to a variety of domains. In the centralized data scenario, this task is commonly solved using deep clustering methods that utilize deep neural network architectures to learn clustering-friendly latent space representations. In Federated Learning, where data is distributed between clients and is private, deep clustering methods are less explored. In particular, recently introduced federated deep clustering methods, despite showing very promising performance, still fall short in reliably providing good performance if data across clients are non-identically-independently distributed. In this work, we introduce a generalization of Deep Clustering Networks to the federated scenario, named FedDCN, that simultaneously optimizes a reconstruction loss and a clustering loss. To ensure robustness and latent space alignment in non-identically-independently distributed data scenarios, FedDCN generates synthetic data augmentations, and its learning objective includes a geometric regularization for latent space alignment. Through experimental evaluation, the effectiveness of the approach under IID and non-IID assumptions is demonstrated, and future research directions are identified.