Timezone: »

 
Poster
Bayesian Semi-supervised Learning with Graph Gaussian Processes
Yin Cheng Ng · Nicolò Colombo · Ricardo Silva

Thu Dec 06 07:45 AM -- 09:45 AM (PST) @ Room 210 #64
in Thu Poster Session A »

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.

Keywords: Gaussian Processes · Semi-Supervised Learning
[ Paper] 

Author Information

Yin Cheng Ng (University College London)
Nicolò Colombo (University College London)
Ricardo Silva (University College London)

More from the Same Authors