Metraipolis › archive › dc_407afc8677e5

Fast Convergence through Distributed Augmentation for Class-Imbalanced Federated Learning — arXiv:2610.05279

Source
arXiv
Original
https://arxiv.org/abs/2610.05279
License (as archived)
CC0-1.0
Archived
2026-10-06T05:30:59.430Z
SHA-256 of the archived text
99d0a90abfba7c01c33ec31abd4e5ec0d0757c69862e2c98ae14f056621f627e
Stable URL of this page
https://metraipolis.com/documento/dc_407afc8677e5

How to cite

Fast Convergence through Distributed Augmentation for Class-Imbalanced Federated Learning — arXiv:2610.05279 — arXiv, https://arxiv.org/abs/2610.05279 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_407afc8677e5 (Metraipolis archive dc_407afc8677e5, sha256 99d0a90abfba7c01c33ec31abd4e5ec0d0757c69862e2c98ae14f056621f627e)
BibTeX
@misc{dc407afc8677e5,
  title = {Fast Convergence through Distributed Augmentation for Class-Imbalanced Federated Learning — arXiv:2610.05279},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05279},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_407afc8677e5; sha256 99d0a90abfba7c01c33ec31abd4e5ec0d0757c69862e2c98ae14f056621f627e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05279. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In federated learning, mitigating class imbalance is essential to improve minority-class performance. A common approach to address this problem is to augment minority-class samples to achieve local class balance. Existing approaches treat augmentation as a heuristic and do not establish how the amount of augmentation influences the convergence of federated learning, leading to excessive augmentation and increased training time. To address this limitation, we first establish the relationship between augmentation and the convergence behavior of federated learning. Leveraging this insight, we propose DAFL, a distributed augmentation framework that determines the minimum augmentation required for each client-class pair by jointly minimizing augmentation and training time while constraining global class imbalance, thereby improving minority-class F1-score. Experimental results demonstrate that DAFL consistently improves minority-class F1-score while substantially reducing training time, particularly under severe global class imbalance and high label proportion imbalance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.05279 — 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 2026-10-06T05:27:05.778Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).