遗忘与解释：GNN去遗忘的透明验证
Forget and Explain: Transparent Verification of GNN Unlearning
AI总结：
本文提出了一种透明的GNN去遗忘验证器，通过快照模型前后状态并利用可解释性指标验证遗忘效果，评估了不同策略在多个基准上的表现。
摘要：
图神经网络（GNNs）越来越多地用于建模图结构数据中的复杂模式。然而，使它们能够“忘记”指定信息仍然具有挑战性，尤其是在隐私法规如GDPR的背景下。现有的去遗忘方法主要优化效率和可扩展性，但它们提供的透明性有限，GNNs的黑盒性质使得难以验证是否真正发生了遗忘。我们提出了一种以可解释性为导向的GNN去遗忘验证器，通过在删除前后快照模型，使用属性偏移和局部结构变化（例如图编辑距离）作为透明的证据。该验证器使用五个可解释性指标：残差属性、热图偏移、可解释性分数偏差、图编辑距离和诊断图规则偏移。我们评估了两种骨干网络（GCN、GAT）和四种去遗忘策略（重新训练、GraphEditor、GNNDelete、IDEA）在五个基准（Cora、Citeseer、Pubmed、Coauthor-CS、Coauthor-Physics）上的表现。结果表明，重新训练和GNNDelete实现了近完全遗忘，GraphEditor提供了部分擦除，而IDEA留下了残余信号。这些解释差异提供了主要的人可读的遗忘证据；我们还报告了成员推断ROC-AUC作为补充的图级隐私信号。
英文摘要：
Graph neural networks (GNNs) are increasingly used to model complex patterns in graph-structured data. However, enabling them to "forget" designated information remains challenging, especially under privacy regulations such as the GDPR. Existing unlearning methods largely optimize for efficiency and scalability, yet they offer little transparency, and the black-box nature of GNNs makes it difficult to verify whether forgetting has truly occurred. We propose an explainability-driven verifier for GNN unlearning that snapshots the model before and after deletion, using attribution shifts and localized structural changes (for example, graph edit distance) as transparent evidence. The verifier uses five explainability metrics: residual attribution, heatmap shift, explainability score deviation, graph edit distance, and a diagnostic graph rule shift. We evaluate two backbones (GCN, GAT) and four unlearning strategies (Retrain, GraphEditor, GNNDelete, IDEA) across five benchmarks (Cora, Citeseer, Pubmed, Coauthor-CS, Coauthor-Physics). Results show that Retrain and GNNDelete achieve near-complete forgetting, GraphEditor provides partial erasure, and IDEA leaves residual signals. These explanation deltas provide the primary, human-readable evidence of forgetting; we also report membership-inference ROC-AUC as a complementary, graph-wide privacy signal.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
