English(EN) Server-Side Sparse Assignment for Federated Mixture-of-Experts

新的 $S^3$-MoE 框架增强了大型语言模型的联邦学习

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

研究人员开发了一个名为 $S^3$-MoE 的新框架，用于在异构边缘设备上对大型语言模型进行联邦学习。这种服务器端稀疏分配方法旨在通过部分观测来提高专家相关性估计，并为误差和恢复提供理论保证。在 CIFAR-100 上的实验表明，$S^3$-MoE 比现有方法实现了更高的准确率，同时减少了客户端的专家加载。 AI

影响该框架可以实现更高效、更私密的在各种边缘设备上对 LLM 进行微调。

排序理由该集群包含一篇详细介绍联邦学习新框架的研究论文。[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: 17 / 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研究论文。[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。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Xue Zheng, Aylin Yener · 2026-11-06 05:00

面向联邦混合专家的服务器端稀疏分配

arXiv:2611.07093v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly recognized for their remarkable capabilities; federated learning (FL) offers a promising framework for collaboratively fine-tuning LLMs on edge devices while achieving data privacy. Howe…

本文如何被排名

报道来源 [1]

面向联邦混合专家的服务器端稀疏分配

相关实体

相关话题