Graph Convolutional Gaussian Processes

Ian Walker, Ben Glocker
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:6495-6504, 2019.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-walker19a, title = {Graph Convolutional {G}aussian Processes}, author = {Walker, Ian and Glocker, Ben}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {6495--6504}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/walker19a/walker19a.pdf}, url = {https://proceedings.mlr.press/v97/walker19a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Graph Convolutional Gaussian Processes %A Ian Walker %A Ben Glocker %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-walker19a %I PMLR %P 6495--6504 %U https://proceedings.mlr.press/v97/walker19a.html %V 97 %X 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.
APA
Walker, I. & Glocker, B.. (2019). Graph Convolutional Gaussian Processes. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:6495-6504 Available from https://proceedings.mlr.press/v97/walker19a.html.

Related Material