Timezone: »
Poster
Graph Convolutional Gaussian Processes
Ian Walker · Ben Glocker
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)
-
2019 Oral: Graph Convolutional Gaussian Processes »
Wed. Jun 12th 06:20 -- 06:25 PM Room Room 101
More from the Same Authors
-
2023 Poster: High Fidelity Image Counterfactuals with Probabilistic Causal Models »
Fabio De Sousa Ribeiro · Tian Xia · Miguel Monteiro · Nick Pawlowski · Ben Glocker -
2018 Poster: Semi-Supervised Learning via Compact Latent Space Clustering »
Konstantinos Kamnitsas · Daniel C. Castro · Loic Le Folgoc · Ian Walker · Ryutaro Tanno · Daniel Rueckert · Ben Glocker · Antonio Criminisi · Aditya Nori -
2018 Oral: Semi-Supervised Learning via Compact Latent Space Clustering »
Konstantinos Kamnitsas · Daniel C. Castro · Loic Le Folgoc · Ian Walker · Ryutaro Tanno · Daniel Rueckert · Ben Glocker · Antonio Criminisi · Aditya Nori