基于子图虚拟边重构的时空图遗忘学习
Unlearning on Spatio-Temporal Graphs through Subgraph Virtual Edge Reconstruction
浏览论文内容
中文总结 AI 辅助
针对时空图节点遗忘效率低的问题，提出受胼胝体启发的CallosumNet框架，通过子图虚拟边重构和元图集成层实现高效完全遗忘，在四个数据集上保持高准确率。
中文摘要 AI 辅助
时空图被广泛用于建模复杂动态过程，如时间序列预测、分子动力学和医疗保健监测。近期，GDPR和CCPA等严格的隐私法规给现有时空图模型带来了重大新挑战，要求对未授权数据进行完全遗忘。由于时空图中的每个节点会在空间和时间维度上全局扩散信息，现有主要为静态图和局部数据移除设计的遗忘方法，无法高效擦除单个节点，且成本几乎等同于全模型重训练。为解决该问题，我们提出CallosumNet，一种受胼胝体结构启发的时空图遗忘学习框架。CallosumNet有两项关键技术贡献：（1）使用受生物学启发的虚拟边重构子图；（2）通过轻量级元图集成层恢复子图间相互关联的时空依赖关系。在四个不同的真实世界数据集上的实验结果表明，CallosumNet可实现完全遗忘，同时保持与最优模型非常接近的准确率。代码已公开于此https URL。
英文摘要
Spatio-temporal graphs are widely used in modeling complex dynamic processes such as temporal forecasting, molecular dynamics, and healthcare monitoring. Recently, stringent privacy regulations such as GDPR and CCPA have introduced significant new challenges for existing spatio-temporal graph models, requiring complete unlearning of unauthorized data. Since each node in a spatio-temporal graph diffuses information globally across both spatial and temporal dimensions, existing unlearning methods primarily designed for static graphs and localized data removal cannot efficiently erase a single node without incurring costs nearly equivalent to full model retraining. To address this, we propose CallosumNet, a spatio-temporal graph unlearning framework biologically inspired by the corpus callosum structure. CallosumNet makes two key technical contributions: (1) it reconstructs subgraphs using biologically-inspired virtual edges; and (2) it restores interlinked spatio-temporal dependencies among subgraphs via a lightweight meta-graph integration layer. Empirical results on four diverse real-world datasets show that CallosumNet achieves complete unlearning while maintaining accuracy very close to the gold model. The code is publicly available at https://github.com/wenlu-lab/STGraphUnlearning.
发表机构
- Texas A&M University - Corpus Christi（德州农工大学科珀斯克里斯蒂分校）
- Delft University of Technology（代尔夫特理工大学）
- University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
- Biogen（渤健公司）
机构由 AI 辅助整理，请以论文原文为准。
