用柯普曼理论解析时序图神经网络，找关键时空模式。
Interpreting Temporal Graph Neural Networks with Koopman Theory
- 基于柯普曼理论，用DMD和SINDy提取动态特征。
- 在合成与真实数据上准确识别感染时间与关键节点。
- 适合研究模型可解释性或时序图分析的学者。
时空图神经网络（STGNN）在预测、流行病学等多个领域表现优异，但其学习到的动态机制难以解释，远超静态数据模型。受柯普曼理论启发——该理论能简洁描述复杂非线性动力系统——我们提出两种新型可解释性方法，用于解析STGNN的决策过程，并识别对任务至关重要的空间与时间模式。第一种方法采用动态模态分解（DMD），一种受柯普曼启发的降维技术；第二种方法使用稀疏非线性动力学识别（SINDy），首次将其作为通用可解释性工具应用。在半合成传播数据集上，方法成功识别出感染发生时刻及感染者节点等可解释特征。在真实人体动作数据集上也进行了定性验证，解释结果突出了动作识别中最相关的身体部位。
原文摘要 · Abstract (English)
Spatiotemporal graph neural networks (STGNNs) have shown promising results in many domains, from forecasting to epidemiology. However, understanding the dynamics learned by these models and explaining their behaviour is significantly more difficult than for models that deal with static data. Inspired by Koopman theory, which allows a simple description of intricate, nonlinear dynamical systems, we introduce new explainability approaches for temporal graphs. Specifically, we present two methods to interpret the STGNN's decision process and identify the most relevant spatial and temporal patterns in the input for the task at hand. The first relies on dynamic mode decomposition (DMD), a Koopman-inspired dimensionality reduction method. The second relies on sparse identification of nonlinear dynamics (SINDy), a popular method for discovering governing equations of dynamical systems, which we use for the first time as a general tool for explainability. On semi-synthetic dissemination datasets, our methods correctly identify interpretable features such as the times at which infections occur and the infected nodes. We also validate the methods qualitatively on a real-world human motion dataset, where the explanations highlight the body parts most relevant for action recognition.
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。