为带符号图设计可证明隐私保护的删减方法，保留重要关系信息。
Certified Signed Graph Unlearning
- 基于三角结构识别受影响最小邻域，高效定位需删数据。
- 结合社会学理论分配隐私预算，实现精准权重更新。
- 在保持模型性能前提下，确保删减过程有数学证明保障。
带符号图通过正负边建模复杂关系，在现实中有广泛应用。鉴于此类数据敏感性，选择性删除机制对隐私保护至关重要。尽管图反学习能移除特定数据对图神经网络（GNN）的影响，但现有方法针对普通GNN设计，忽略带符号图的异质特性。应用于带符号图神经网络（SGNN）时，这些方法会丢失关键符号信息，导致模型效用与删减效果双重下降。为此，我们提出认证式带符号图反学习（CSGU），在保证社会学原则的同时提供可证明的隐私保障。CSGU采用三阶段策略：(1) 利用三角结构高效识别最小影响邻域；(2) 基于社会学理论量化节点重要性，优化隐私预算分配；(3) 实施重要性加权参数更新，实现认证修改且效用损失最小。大量实验表明，相较于现有方法，CSGU在SGNN上显著提升效用保持与反学习效果。
原文摘要 · Abstract (English)
Signed graphs model complex relationships through positive and negative edges, with widespread real-world applications. Given the sensitive nature of such data, selective removal mechanisms have become essential for privacy protection. While graph unlearning enables the removal of specific data influences from Graph Neural Networks (GNNs), existing methods are designed for conventional GNNs and overlook the unique heterogeneous properties of signed graphs. When applied to Signed Graph Neural Networks (SGNNs), these methods lose critical sign information, degrading both model utility and unlearning effectiveness. To address these challenges, we propose Certified Signed Graph Unlearning (CSGU), which provides provable privacy guarantees while preserving the sociological principles underlying SGNNs. CSGU employs a three-stage method: (1) efficiently identifying minimal influenced neighborhoods via triangular structures, (2) applying sociological theories to quantify node importance for optimal privacy budget allocation, and (3) performing importance-weighted parameter updates to achieve certified modifications with minimal utility degradation. Extensive experiments demonstrate that CSGU outperforms existing methods, achieving superior performance in both utility preservation and unlearning effectiveness on SGNNs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。