English(EN) Theoretically Principled Federated Learning for Balancing Privacy and Utility

新的联邦学习框架平衡隐私和效用

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-27 04:00

研究人员开发了一个新的联邦学习框架，旨在平衡隐私和效用。该框架允许在每个客户端和每个回合的基础上对模型参数进行自适应和细粒度的保护。理论分析表明，与最优保护相比，效用损失差距随着迭代次数的增加呈亚线性增长，并且在基准数据集上的实证结果证实了在相同的隐私预算下，其效用优于基线方法。 AI

影响这项研究可能有助于在分布式环境中开发更有效的隐私保护机器学习应用。

排序理由该集群包含一篇学术论文，详细介绍了联邦学习的新理论框架和实证结果。[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: 23 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了联邦学习的新理论框架和实证结果。[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: 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) · Xiaojin Zhang, Wenjie Li, Yiming Li, Wei Chen, Shutao Xia, Qiang Yang · 2026-08-27 04:00

理论上原则性的联邦学习，用于平衡隐私和效用

arXiv:2305.15148v3 Announce Type: replace Abstract: We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility. The algorithm is applicable to arbitrary p…