PulseAugur
中
实时 10:38:44
English(EN) RAPTOR: Role-Aware Private Training for Mixture-of-Experts

新的RAPTOR框架增强了MoE AI模型的私有训练

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员开发了RAPTOR，一种用于专家混合（MoE）模型差分私有训练的新颖框架。现有方法将这些稀疏模型视为密集块，导致梯度抑制和更新稀释等问题。RAPTOR通过交替共享和专家优化、采用专家特定裁剪和噪声，以及使用无隐私规则来选择免受路由熵影响的层来解决这些问题。在Switch Transformer和OLMoE等模型上的实验表明，与标准的DP基线相比，性能持续提升，尤其是在更严格的隐私预算下。 AI

影响 增强了大型稀疏AI模型的隐私保证，可能促使其在敏感应用中得到更广泛的应用。

排序理由 该集群描述了一篇介绍AI模型新颖训练框架的研究论文。[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 →

新的RAPTOR框架增强了MoE AI模型的私有训练

本文如何被排名

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一篇介绍AI模型新颖训练框架的研究论文。[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, safety
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
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Duc Dm, Khai Le-Duc, Nguyen Do, Minh Son Hoang, Florent Draye, Thai Hoang, Hoang Phuong Dam, Jiarui Liu, Chris Ngo, Terry Jingchen Zhang, Anh Le Duc Tran, Nhat Do Minh, Minh Ngoc Le, My T. Thai, Ran Xu, Silvio Savarese, Mona Diab, Bernhard Sch\"olkopf, Z… ·

    RAPTOR：面向专家混合模型的角色感知私有训练

    arXiv:2609.05770v1 Announce Type: new Abstract: Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see all data while experts only see routed records. We identify and formally character…

相关实体

相关话题