Interpreting Temporal Graph Neural Networks with Koopman Theory

ArXi:2410.13469v2 Announce Type: replace 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 difficult than for models that deal with static data. Inspired by Koopman theory, which allows a simple description of intricate, nonlinear dynamical systems, we