graph convolutional neural networks (GCNN) have numerous applications in
different graph based learning tasks. Although the techniques obtain impressive
results, they often fall short in accounting for the uncertainty associated
with the underlying graph structure. In the recently prop
本论文介绍了一种新算法 ——Bayesian Graph Convolutional Network using Neighborhood Random Walk Sampling (BGCN-NRWS),使用基于 Markov Chain Monte Carlo (MCMC) 的图采样算法利用图结构,通过使用变分推断层来减少过拟合,并且在半监督节点分类方面与现有技术保持竞争性结果。