PulseAugur
中
实时 06:40:28

Federated Learning uses spectral entropy for data-free client contribution estimation

作者 PulseAugur 编辑部 · [2 个来源] ·

Researchers have developed a novel method for estimating client contributions in Federated Learning without requiring access to client data. This approach utilizes the spectral entropy of final-layer updates to measure the diversity of information contributed by each client. Two practical schemes, SpectralFed and SpectralFuse, were introduced, demonstrating a strong correlation with client accuracy across various benchmarks and non-IID conditions. AI

影响 Offers a privacy-preserving method for evaluating client contributions in federated learning, potentially improving model aggregation and reward systems.

排序理由 Academic paper introducing a new method for federated learning.

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Federated Learning uses spectral entropy for data-free client contribution estimation

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Asim Ukaye, Mubarak Abdu-Aguye, Nurbek Tastan, Karthik Nandakumar ·

    Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy

    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…

  2. arXiv cs.CV TIER_1 English(EN) · Karthik Nandakumar ·

    Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy

    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…

相关实体

相关话题