Skip to yearly menu bar Skip to main content


Graph Convolutional Gaussian Processes

Ian Walker · Ben Glocker

Pacific Ballroom #212

Keywords: [ Gaussian Processes ] [ Bayesian Nonparametrics ] [ Bayesian Methods ]


We propose a novel Bayesian nonparametric method to learn translation-invariant relationships on non-Euclidean domains. The resulting graph convolutional Gaussian processes can be applied to problems in machine learning for which the input observations are functions with domains on general graphs. The structure of these models allows for high dimensional inputs while retaining expressibility, as is the case with convolutional neural networks. We present applications of graph convolutional Gaussian processes to images and triangular meshes, demonstrating their versatility and effectiveness, comparing favorably to existing methods, despite being relatively simple models.

Live content is unavailable. Log in and register to view live content