Graph convolutional Gaussian processes

We propose a novel Bayesian nonparametricmethod to learn translation-invariant relationshipson non-Euclidean domains. The resulting graphconvolutional Gaussian processes can be appliedto problems in machine learning for which theinput observations are functions with domains ongeneral graphs. The structure of these models al-lows for high dimensional inputs while retainingexpressibility, as is the case with convolutionalneural networks. We present applications of graphconvolutional Gaussian processes to images andtriangular meshes, demonstrating their versatilityand effectiveness, comparing favorably to existingmethods, despite being relatively simple models