PulseAugur
中
实时 12:00:30
English(EN) EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy

EdgeRefine 框架提高了图神经网络中的隐私-效用平衡

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了 EdgeRefine，一个旨在提高图神经网络 (GNN) 中隐私-效用平衡的新颖框架。该方法通过采用自适应边缘精炼和 Jaccard 相似度进行边缘概率估计，解决了图数据中敏感链接信息泄露的挑战。EdgeRefine 旨在在保持强大隐私保证的同时提高准确性，在 ACM 和 Cora 等基准数据集上显著优于现有方法。 AI

影响 通过改善数据效用和隐私之间的权衡，增强了图神经网络在隐私敏感应用中的可行性。

排序理由 该集群包含一篇学术论文，详细介绍了一种新的隐私保护图学习方法。

在 arXiv cs.LG 阅读 →

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

EdgeRefine 框架提高了图神经网络中的隐私-效用平衡

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Wenxiu Ding, Muzhi Liu, Zheng Yan, Mingjun Wang, Yifan Zhao, Qiao Liu ·

    EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy

    arXiv:2607.08659v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains difficult because graph structure can leak sensitive link information. To satisfy …

  2. arXiv cs.LG TIER_1 English(EN) · Qiao Liu ·

    EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy

    Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains difficult because graph structure can leak sensitive link information. To satisfy edge-level differential privacy, a common approa…

相关实体

相关话题