Metraipolis › archive › dc_2e105967da74
Global Federated Learning Strategies for Building Efficient Personalized Models — arXiv:2608.15107
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15107
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:40:01.080Z
- SHA-256 of the archived text
77d38dca99ffd9e1761289cc71cd5b85c12a5c6c6c351a532c2ca488b5e64993- Stable URL of this page
https://metraipolis.com/documento/dc_2e105967da74
How to cite
Global Federated Learning Strategies for Building Efficient Personalized Models — arXiv:2608.15107 — arXiv (en), https://arxiv.org/abs/2608.15107 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e105967da74 (Metraipolis archive dc_2e105967da74, sha256 77d38dca99ffd9e1761289cc71cd5b85c12a5c6c6c351a532c2ca488b5e64993)
BibTeX
@misc{dc2e105967da74,
title = {Global Federated Learning Strategies for Building Efficient Personalized Models — arXiv:2608.15107},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15107},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e105967da74; sha256 77d38dca99ffd9e1761289cc71cd5b85c12a5c6c6c351a532c2ca488b5e64993},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15107. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Federated learning (FL) is a practical framework that can train models on distributed user data while guaranteeing data privacy; however, due to heterogeneity in which each user has a different data distribution, problems frequently arise where both global and personalization performance deteriorate simultaneously. This dissertation presents methodologies for building efficient personalized models by identifying which strategies are effective in the global training stage and by showing how to preserve global knowledge while securing user-specific performance during local adaptation. First, we show that as data heterogeneity increases, the collapse of feature vectors is a more fundamental bottleneck than classifier weights, and propose a method that directly mitigates the discrepancy in representation magnitude between local and global models. Second, we analyze that a training approach that strengthens local alignment can induce forgetting of global knowledge (e.g., categories not observed locally), and propose a method that achieves both local alignment and global knowledge preservation by combining feature distillation based on the global model's feature vectors. Third, in federated personalized reward model learning with preference heterogeneity, we empirically verify the conventional belief that "increasing the number of global models yields better initialization," and we show that when sufficient local fine-tuning is allowed, a single global initialization can instead provide stronger personalization performance. This study redefines the role of global initialization under data and preference heterogeneity and provides practical training strategies that simultaneously satisfy global knowledge preservation and personalization. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.15107 — 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 2026-10-18T19:02:44.074Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).