Metraipolis › archive › dc_d187f014572f

CALM: Class-wise Agreement and Label-gated Disagreement Modulation for Decentralized Federated Learning — arXiv:2609.05884

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05884
License (as archived)
CC0-1.0
Archived
2026-10-16T13:07:24.361Z
SHA-256 of the archived text
83e059e0e1a32f782ad0a314fd55f19b59596df3df7b2e657850d0e9f5fb4d55
Stable URL of this page
https://metraipolis.com/documento/dc_d187f014572f

How to cite

CALM: Class-wise Agreement and Label-gated Disagreement Modulation for Decentralized Federated Learning — arXiv:2609.05884 — arXiv (en), https://arxiv.org/abs/2609.05884 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d187f014572f (Metraipolis archive dc_d187f014572f, sha256 83e059e0e1a32f782ad0a314fd55f19b59596df3df7b2e657850d0e9f5fb4d55)
BibTeX
@misc{dcd187f014572f,
  title = {CALM: Class-wise Agreement and Label-gated Disagreement Modulation for Decentralized Federated Learning — arXiv:2609.05884},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05884},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d187f014572f; sha256 83e059e0e1a32f782ad0a314fd55f19b59596df3df7b2e657850d0e9f5fb4d55},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05884. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conventional federated learning relies on parameter averaging, which forces clients to be doubly homogeneous: all must run an identical architecture, and accuracy degrades when local data are non-IID. Decentralized federated distillation sidesteps both: each client runs its peers' model snapshots as teachers on its own local data and distills from their soft predictions, with no server, no public data, and no shared architecture. Under severe non-IID skew, however, the trustworthiness of the aggregated teacher target is a matter of degree, yet existing pipelines make hard, all-or-nothing decisions: outlier teachers are discarded by threshold, and whatever target survives is trusted in full. We propose CALM, which replaces every hard decision with a smooth trust gate at three levels: per class, teachers are weighted by agreement with the peer consensus; per sample, distillation is scaled by the teachers' divergence from that target; and a label gate scales it by how strongly the target supports the sample's true label. None of this adds communication or auxiliary data. On CIFAR-10, SVHN, OrganAMNIST, and Google Speech Commands with heterogeneous client architectures under Dirichlet label skew, CALM consistently outperforms uniform and hard-filtered distillation and matches or exceeds competing heterogeneous-FL methods.

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/2609.05884 — 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 2026-10-16T13:02:21.606Z 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).