English(EN) Personalized Federated Learning for Gradient Alignment

联邦学习研究探索结构和梯度对齐以实现个性化

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-05 04:00

两篇新研究论文提出了改进联邦学习的新方法，特别是在客户端数据和模型架构各异的异构环境中。第一篇论文《从坐标匹配到结构对齐》（From Coordinate Matching to Structural Alignment）介绍了 FedSAF，该方法将特征表示的对齐从基于绝对坐标转移到基于类间关系结构进行对齐，性能提升高达 3.52%。第二篇论文《用于梯度对齐的个性化联邦学习》（Personalized Federated Learning for Gradient Alignment）提出了 pFLAlign 框架，该框架通过调整局部梯度方向和重新对齐全局模型，旨在在局部训练和聚合过程中维护客户端特定信息。 AI

影响这些论文为在数据和架构多样化的分布式学习环境中增强模型个性和性能提供了新方法。

排序理由两篇 arXiv 论文介绍了联邦学习的新技术。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Xinghao Wu, Jianwei Niu, Guogang Zhu, Xuefeng Liu, Shaojie Tang, Jiayuan Zhang · 2026-05-08 04:00

From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning

arXiv:2605.05959v1 Announce Type: cross Abstract: Heterogeneous federated learning (HtFL) aims to enable collaboration among clients that differ in both data distributions and model architectures. Prototype-based methods, which communicate class-level feature centers (prototypes)…
arXiv cs.LG TIER_1 English(EN) · Dongwon Kim, Gyuejeong Lee · 2026-05-05 04:00

Personalized Federated Learning for Gradient Alignment

arXiv:2605.02143v1 Announce Type: new Abstract: Personalized federated learning (pFL) aims to adapt models to client specific data distributions, yet it often fails to reliably preserve personalized information. Local training is hindered by high variance gradients induced by lim…

报道来源 [2]

From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning

Personalized Federated Learning for Gradient Alignment

相关实体

相关话题