Metraipolis › archive › dc_f2b5eca37e38
FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning — arXiv:2608.09221
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09221
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:52:51.040Z
- SHA-256 of the archived text
878b4aa62bc1834c4bc9056fbd4e46fe661d0ada6399432a220cdd6e972f81df- Stable URL of this page
https://metraipolis.com/documento/dc_f2b5eca37e38
How to cite
FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning — arXiv:2608.09221 — arXiv (en), https://arxiv.org/abs/2608.09221 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f2b5eca37e38 (Metraipolis archive dc_f2b5eca37e38, sha256 878b4aa62bc1834c4bc9056fbd4e46fe661d0ada6399432a220cdd6e972f81df)
BibTeX
@misc{dcf2b5eca37e38,
title = {FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning — arXiv:2608.09221},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09221},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f2b5eca37e38; sha256 878b4aa62bc1834c4bc9056fbd4e46fe661d0ada6399432a220cdd6e972f81df},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09221. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Federated Learning (FL) enables collaborative model training across distributed client devices while preserving data privacy. However, FL faces significant challenges due to data heterogeneity, particularly in terms of label distribution skewness and variations in dataset sizes, which can lead to biased model updates and hinder convergence. To address this, we propose FedTVD, a novel FL algorithm that weights client contributions during aggregation by considering both data quality and quantity. Unlike traditional FL approaches such as FedAvg, which rely solely on dataset size for client weighting, FedTVD integrates Total Variation Distance (TVD) to measure the divergence between each client's local label distribution and a uniform global distribution. Clients with highly skewed distributions receive lower weights, preventing unbalanced datasets with imbalances from disproportionately influencing the global model. At the same time, dataset size is incorporated to ensure scalability and fairness. This dual-weighting mechanism effectively mitigates the impact of data imbalance, leading to more stable and generalized global models. Experimental results show that FedTVD consistently outperforms state-of-the-art methods across all datasets (FMNIST, CIFAR-10, and CIFAR-100) and all levels of data heterogeneity. Notably, it achieves up to 10.6% improvement over FedAvg on CIFAR-10 under highly skewed data, while maintaining top performance even under moderate and IID settings. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-11 in cs.DC). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2608.09221 — 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 2026-10-19T08:50:23.786Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).