Neighborhood Random Walk Graph Sampling for Regularized Bayesian Graph Convolutional Neural Networks

TL;DR

This paper introduces BGCN-NRWS, a Bayesian graph convolutional network that employs neighborhood random walk sampling and variational inference to improve semi-supervised node classification on noisy graphs.

Contribution

It proposes a novel MCMC-based graph sampling method that incorporates graph structure and reduces overfitting in Bayesian GCNs.

Findings

Achieves competitive accuracy on benchmark datasets.

Effectively models uncertainty in noisy graph data.

Reduces overfitting through variational inference layer.

Abstract

In the modern age of social media and networks, graph representations of real-world 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 graph-based models, specifically for semi-supervised 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 (BGCN-NRWS), 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 state-of-the-art in semi-supervised node classification.