Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Bayesian Decision-making and Uncertainty: from probabilistic and spatiotemporal modeling to sequential experiment design

Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations

Richard Bergna · Sergio Calvo Ordoñez · Felix Opolka · Pietro Lió · José Miguel Hernández-Lobato

Keywords: [ graph neural networks ] [ bayesian inference ] [ uncertainty quantification ] [ Neural SDEs ] [ stochastic differential equations ]


Abstract:

We address the problem of learning uncertainty-aware representations for graph-structured data. While Graph Neural Ordinary Differential Equations (GNODE) are effective in learning node representations, they fail to quantify uncertainty. To address this, we introduce Latent Graph Neural Stochastic Differential Equations (LGNSDE), which enhance GNODE by embedding randomness through Brownian motion to quantify uncertainty. We provide theoretical guarantees for LGNSDE and empirically show better performance in uncertainty quantification.

Chat is not available.