Bayesian semi-supervised learning with graph Gaussian processes. / Ng, Yin Cheng; Colombo, Nicolò; Silva, Ricardo.

In: ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS, Vol. 2018-December, 03.12.2018, p. 1690-1701.

Research output: Contribution to journalConference article

Published

Links

Abstract

We propose a data-efficient Gaussian process-based Bayesian approach to the semi-supervised learning problem on graphs. The proposed model shows extremely competitive performance when compared to the state-of-the-art graph neural networks on semi-supervised learning benchmark experiments, and outperforms the neural networks in active learning experiments where labels are scarce. Furthermore, the model does not require a validation data set for early stopping to control over-fitting. Our model can be viewed as an instance of empirical distribution regression weighted locally by network connectivity. We further motivate the intuitive construction of the model with a Bayesian linear model interpretation where the node features are filtered by an operator related to the graph Laplacian. The method can be easily implemented by adapting off-the-shelf scalable variational inference algorithms for Gaussian processes.

Original languageEnglish
Pages (from-to)1690-1701
Number of pages12
JournalADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS
Volume2018-December
Publication statusPublished - 3 Dec 2018
Event32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
Duration: 2 Dec 20188 Dec 2018
This open access research output is licenced under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.

ID: 34305124