Metraipolis › archive › dc_a6283bd676ca
Federated Deep Clustering Networks for High-Dimensional and Heterogeneous Data — arXiv:2609.21829
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.21829
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T01:12:51.654Z
- SHA-256 of the archived text
580eee42d377451ab66dee34c0867cba59189ffc8b853fc663b534d93525b7c6- Stable URL of this page
https://metraipolis.com/documento/dc_a6283bd676ca
How to cite
Federated Deep Clustering Networks for High-Dimensional and Heterogeneous Data — arXiv:2609.21829 — arXiv (en), https://arxiv.org/abs/2609.21829 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6283bd676ca (Metraipolis archive dc_a6283bd676ca, sha256 580eee42d377451ab66dee34c0867cba59189ffc8b853fc663b534d93525b7c6)
BibTeX
@misc{dca6283bd676ca,
title = {Federated Deep Clustering Networks for High-Dimensional and Heterogeneous Data — arXiv:2609.21829},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.21829},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6283bd676ca; sha256 580eee42d377451ab66dee34c0867cba59189ffc8b853fc663b534d93525b7c6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21829. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.21829 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T00:23:42.569Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).