Metraipolis › archive › dc_5d0cc989c034
Robust Decentralized Federated Distillation via Multi-Modality Knowledge Collaboration — arXiv:2609.07230
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07230
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:07:28.329Z
- SHA-256 of the archived text
047c1b8999d38f0f163d0b6d8983fe86076c71e361b2a7af485d918a99010d6f- Stable URL of this page
https://metraipolis.com/documento/dc_5d0cc989c034
How to cite
Robust Decentralized Federated Distillation via Multi-Modality Knowledge Collaboration — arXiv:2609.07230 — arXiv (en), https://arxiv.org/abs/2609.07230 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5d0cc989c034 (Metraipolis archive dc_5d0cc989c034, sha256 047c1b8999d38f0f163d0b6d8983fe86076c71e361b2a7af485d918a99010d6f)
BibTeX
@misc{dc5d0cc989c034,
title = {Robust Decentralized Federated Distillation via Multi-Modality Knowledge Collaboration — arXiv:2609.07230},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07230},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5d0cc989c034; sha256 047c1b8999d38f0f163d0b6d8983fe86076c71e361b2a7af485d918a99010d6f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07230. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper propose a robust decentralized federated distillation method that enables clients with heterogeneous models to collaborate through predictions on shared unlabeled public data. In the proposed method, each client first evaluates the received predictions in three modalities of class prediction, boundary decision, and prediction correlation. It then filters unreliable clients, assigns reliability-based weights to the retained clients, and constructs a teacher for each type of knowledge. Finally, the corresponding distillation gradients are validated using a supervised gradient computed from private data. Conflicting prediction and boundary gradients are removed, and conflicting relation gradients are suppressed before the final model update. We prove the convergence of the proposed method by showing stable local optimization for honest clients under Byzantine distillation. Particularly, we show that our method ensures a bounded Byzantine influence on both distillation gradients and individual client private gradients after cross-modality fusion, thereby enabling stable local optimization for honest clienunder Byzantine distillation. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate that the proposed method improves the prediction accuracy of heterogeneous models of clients under non-IID data and Byzantine attacks. As the booming demands of federated learning in decentralized environments such as edge computing and mission-oriented UAV collaborations, our method has a great potential for adoption of DFL in unreliable real-world scenarios where clients are exposed to receiver-specific Byzantine messages of malicious predictions. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-09 in cs.DC). Categorie arXiv: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2609.07230 — 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 2026-10-16T13:02:21.616Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).