Timezone: »

Graph Convolutional Gaussian Processes
Ian Walker · Ben Glocker

Wed Jun 06:30 PM -- 09:00 PM PDT @ Pacific Ballroom #212

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.

Author Information

Ian Walker (Imperial College London)
Ben Glocker (Imperial College London)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors