Graph Neural Stochastic Differential Equations
This addresses the need for uncertainty quantification in graph-based models, which is crucial for reliable predictions in domains like spatio-temporal data, though it appears incremental as an enhancement to existing Graph Neural ODEs.
The paper tackles the problem of prediction uncertainty in graph neural networks by introducing Graph Neural Stochastic Differential Equations, which embed randomness using Brownian motion to assess uncertainty. The result shows that Latent Graph Neural SDEs outperform conventional models like Graph Convolutional Networks and Graph Neural ODEs, particularly in confidence prediction and out-of-distribution detection.
We present a novel model Graph Neural Stochastic Differential Equations (Graph Neural SDEs). This technique enhances the Graph Neural Ordinary Differential Equations (Graph Neural ODEs) by embedding randomness into data representation using Brownian motion. This inclusion allows for the assessment of prediction uncertainty, a crucial aspect frequently missed in current models. In our framework, we spotlight the \textit{Latent Graph Neural SDE} variant, demonstrating its effectiveness. Through empirical studies, we find that Latent Graph Neural SDEs surpass conventional models like Graph Convolutional Networks and Graph Neural ODEs, especially in confidence prediction, making them superior in handling out-of-distribution detection across both static and spatio-temporal contexts.