English(EN) Private and Distributionally Robust Federated Multiclass Classification

新框架提供私有和鲁棒的联邦多类别分类

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-12 04:00

研究人员开发了一种新的联邦多类别分类框架，该框架同时提供差分隐私和分布鲁棒性。这种方法能够在不集中敏感数据的情况下，跨多个站点进行协作模型训练，同时保护个体记录并处理标签噪声。该方法利用具有 Crammer-Singer 损失的差分隐私联邦 Wasserstein 分布鲁棒目标，并通过基于 ADMM 的算法求解。实验表明，与现有的差分隐私联邦方法相比，该方法在严格的隐私约束下尤其有效。 AI

影响增强了敏感数据协作式人工智能模型训练中的隐私和鲁棒性。

排序理由该集群包含一篇详细介绍联邦多类别分类新框架的研究论文。[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: 11 / 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多类别分类新框架的研究论文。[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, safety, 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: 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]

arXiv cs.LG TIER_1 English(EN) · Andrea P. Hernandez, Michael Ibrahim, Nagi Gebraeel · 2026-10-12 04:00

私有和分布鲁棒的联邦多类别分类

arXiv:2610.13631v1 Announce Type: new Abstract: Fault diagnosis in asset-intensive industries requires multiclass models trained on noisy, sensitive data collected across geographically distributed client sites. Federated learning enables collaborative training without centralizi…

本文如何被排名

报道来源 [1]

私有和分布鲁棒的联邦多类别分类

相关实体

相关话题