English(EN) PSL-RGHA: Parallel Split Learning with Reference Gradient Half-Space Alignment for Mitigating Gradient Divergence

新的PSL-RGHA框架解决了联邦学习中的发散问题

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

研究人员推出了一种新颖的并行拆分学习框架PSL-RGHA，旨在解决联邦学习中的训练发散问题。该方法利用参考梯度渐进构建和梯度半空间对齐来创建鲁棒的参考梯度并约束客户端更新，从而提高收敛性和性能，尤其是在多媒体应用中资源受限的设备上。 AI

影响该框架可以实现资源有限设备上更高效的联邦学习，特别是在多媒体任务方面。

排序理由该集群包含一篇详细介绍联邦学习新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

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: 34 / 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方法的论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Han Li, Zheng Lin, Miao Yang, Zehang Lin, Jing Yang, Zihan Fang, Qiyang Zhang, Zhaolu Kang, Jianmin Li, Lin Li, Mingwei Hong, Shunzhi Zhu · 2026-11-11 05:00

PSL-RGHA：用于缓解梯度发散的具有参考梯度半空间对齐的并行拆分学习

arXiv:2611.14312v1 Announce Type: new Abstract: The escalating complexity of deep neural networks hinders the deployment of federated learning (FL) on resource-constrained devices, especially for multimedia applications such as on-device image classification and speech recognitio…