提出生物启发的图学习遗忘框架，高效删除动态图中单个节点数据。
Unlearning on Spatio-Temporal Graphs through Subgraph Virtual Edge Reconstruction
- 用虚拟边重构子图，模拟大脑胼胝体连接机制。
- 在4个真实数据集上实现完全遗忘，精度接近原模型。
- 适合需要合规删除敏感数据的时空建模场景。
时空图广泛用于建模复杂动态过程，如时间预测、分子动力学和医疗监测。随着GDPR和CCPA等严格隐私法规的出台，现有时空图模型面临新挑战：必须彻底删除未经授权的数据。由于时空图中每个节点的信息会同时向空间和时间维度全局扩散，现有针对静态图和局部数据移除的方法无法高效删除单个节点，其成本几乎等同于全量重训练。为此，本文提出CallosumNet，一种受大脑胼胝体结构启发的时空图遗忘框架。该框架包含两项关键技术：（1）通过生物启发的虚拟边重建子图；（2）利用轻量级元图集成层恢复子图间的时空关联。在四个不同真实数据集上的实验表明，CallosumNet实现了完全遗忘，且性能与基准模型极为接近。代码已公开于https://github.com/wenlu-lab/STGraphUnlearning。
原文摘要 · Abstract (English)
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.
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。