English(EN) Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning

新的 XCal-FL 算法增强了差分隐私联邦学习的可解释性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-04 04:00

研究人员开发了 XCal-FL，这是一种新颖的联邦学习算法，它动态校准差分隐私噪声以增强可解释性。这个闭环系统在训练过程中使用预测logit变化、反事实边际和显著性集中来调整噪声水平，从而提高模型准确性和解释的可靠性。实验表明，XCal-FL 在提高模型准确性和解释的可靠性方面显著优于静态噪声联邦学习和其他自适应 DP 方法，特别是在医疗诊断等关键决策应用中，它提供了更好的隐私预算效率和超越单纯预测性能的可解释性维度。 AI

影响通过提高敏感应用中 AI 模型的可解释性以及隐私性，增强了其可信度。

排序理由该集群包含一篇详细介绍新算法及其实验结果的学术论文。[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: 15 / 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新算法及其实验结果的学术论文。[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: 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。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Michael Khavkin, Kichang Lee, Jaeho Jin, JeongGil Ko, Eran Toch · 2026-09-04 04:00

突破（决策）界限：在联邦学习中动态校准差分隐私噪声以实现可解释性

arXiv:2609.03851v1 Announce Type: new Abstract: Federated Learning (FL) with Differential Privacy (DP) is increasingly adopted to preserve data confidentiality in distributed machine learning. However, DP noise distorts learned representations and degrades explanation fidelity, l…

本文如何被排名

报道来源 [1]

突破（决策）界限：在联邦学习中动态校准差分隐私噪声以实现可解释性

相关实体

相关话题