Neighborhood Random Walk Graph Sampling for Regularized Bayesian Graph Convolutional Neural Networks
Abstract
In the modern age of social media and networks, graph representations of realworld phenomena have become an incredibly useful source to mine insights. Often, we are interested in understanding how entities in a graph are interconnected. The Graph Neural Network (GNN) has proven to be a very useful tool in a variety of graph learning tasks including node classification, link prediction, and edge classification. However, in most of these tasks, the graph data we are working with may be noisy and may contain spurious edges. That is, there is a lot of uncertainty associated with the underlying graph structure. Recent approaches to modeling uncertainty have been to use a Bayesian framework and view the graph as a random variable with probabilities associated with model parameters. Introducing the Bayesian paradigm to graphbased models, specifically for semisupervised node classification, has been shown to yield higher classification accuracies. However, the method of graph inference proposed in recent work does not take into account the structure of the graph. In this paper, we propose a novel algorithm called Bayesian Graph Convolutional Network using Neighborhood Random Walk Sampling (BGCNNRWS), which uses a Markov Chain Monte Carlo (MCMC) based graph sampling algorithm utilizing graph structure, reduces overfitting by using a variational inference layer, and yields consistently competitive classification results compared to the stateoftheart in semisupervised node classification.
 Publication:

arXiv eprints
 Pub Date:
 December 2021
 arXiv:
 arXiv:2112.07743
 Bibcode:
 2021arXiv211207743K
 Keywords:

 Computer Science  Machine Learning;
 Statistics  Machine Learning
 EPrint:
 Accepted for publication at the 20th IEEE International Conference on Machine Learning and Applications (ICMLA 2021)