# Bayesian Graph Convolutional Neural Networks using Node Copying

arXiv: https://arxiv.org/abs/1911.04965 · HTML: https://mlsanity.com/paper/1911.04965/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2019.

## Built on by (most cited first, 6 of 6)

- [Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification](https://mlsanity.com/paper/2110.14012/) (2021)
- [Node Copying: A Random Graph Model for Effective Graph Sampling](https://mlsanity.com/paper/2208.02435/) (2022)
- [Uncertainty Quantification on Graph Learning: A Survey](https://mlsanity.com/paper/2404.14642/) (2024)
- [Probabilistic modeling of lake surface water temperature using a Bayesian spatio-temporal graph convolutional neural network](https://mlsanity.com/paper/2109.13235/) (2021)
- [Bayes-enhanced Multi-view Attention Networks for Robust POI Recommendation](https://mlsanity.com/paper/2311.00491/) (2023)
- [Neighborhood Random Walk Graph Sampling for Regularized Bayesian Graph Convolutional Neural Networks](https://mlsanity.com/paper/2112.07743/) (2021)

## Abstract (arXiv)

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 proposed Bayesian GCNN (BGCN) framework, this issue is tackled by viewing the observed graph as a sample from a parametric random graph model and targeting joint inference of the graph and the GCNN weights. In this paper, we introduce an alternative generative model for graphs based on copying nodes and incorporate it within the BGCN framework. Our approach has the benefit that it uses information provided by the node features and training labels in the graph topology inference. Experiments show that the proposed algorithm compares favorably to the state-of-the-art in benchmark node classification tasks.