English(EN) Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy

联邦学习使用谱熵进行无数据客户端贡献估计

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-24 13:55

研究人员开发了一种新颖的方法，可以在不访问客户端数据的情况下估计联邦学习中的客户端贡献。该方法利用最终层更新的谱熵来衡量每个客户端贡献的信息的多样性。引入了两种实用方案 SpectralFed 和 SpectralFuse，它们在各种基准和非独立同分布条件下与客户端准确性显示出很强的相关性。 AI

影响提供了一种用于评估联邦学习中客户端贡献的隐私保护方法，有可能改进模型聚合和奖励系统。

排序理由介绍联邦学习新方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 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: Research; 介绍联邦学习新方法的学术论文。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics: paper, other; 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: 164 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。

arXiv cs.CV TIER_1 English(EN) · Asim Ukaye, Mubarak Abdu-Aguye, Nurbek Tastan, Karthik Nandakumar · 2026-04-27 04:00

使用梯度冯·诺依曼熵在联邦学习中进行无数据贡献估计

arXiv:2604.22562v1 Announce Type: cross Abstract: Client contribution estimation in Federated Learning is necessary for identifying clients' importance and for providing fair rewards. Current methods often rely on server-side validation data or self-reported client information, w…
arXiv cs.CV TIER_1 English(EN) · Karthik Nandakumar · 2026-04-24 13:55

使用梯度冯·诺依曼熵在联邦学习中进行无数据贡献估计

Client contribution estimation in Federated Learning is necessary for identifying clients' importance and for providing fair rewards. Current methods often rely on server-side validation data or self-reported client information, which can compromise privacy or be susceptible to m…