新的GAPSL框架增强了异构边缘系统中的联邦学习

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-04 04:00

研究人员开发了GAPSL，一个用于并行拆分学习的新框架，旨在改善具有异构数据的边缘计算系统中的联邦学习。GAPSL通过引入两个组件来解决由设备间不一致的梯度方向引起的训练发散：领导者梯度识别（LGI）和梯度方向对齐（GDA）。LGI选择一个鲁棒的领导者梯度，而GDA使用正则化将客户端梯度与该领导者对齐，从而增强模型的收敛性和鲁棒性。实验表明，GAPSL在准确性、收敛速度和系统弹性方面优于现有基准。 AI

影响该框架可以提高在数据多样化的边缘设备上训练AI模型的效率和准确性。

排序理由该集群包含一篇详细介绍联邦学习新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍联邦学习新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 64 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Zheng Lin, Ons Aouedi, Zihan Fang, Wei Ni, Yue Gao, Symeon Chatzinotas, Xianhao Chen · 2026-08-04 04:00

GAPSL：数据异构边缘计算系统上的梯度对齐并行拆分学习

arXiv:2603.18540v2 Announce Type: replace Abstract: The increasing complexity of neural networks poses significant challenges for democratizing federated learning (FL) on resource-constrained edge devices. Parallel split learning (PSL) has emerged as a promising solution by offlo…

本文如何被排名

报道来源 [1]

GAPSL：数据异构边缘计算系统上的梯度对齐并行拆分学习

相关实体

相关话题