Non-Parametric Graph Learning for Bayesian Graph Neural Networks
This addresses the issue of unreliable graph representations for researchers and practitioners using graph neural networks, though it appears incremental as it builds on existing Bayesian frameworks.
The paper tackles the problem of inaccurate or noisy graph structures in graph-based learning by proposing a non-parametric Bayesian model for posterior inference of graph adjacency matrices, demonstrating advantages in node classification, link prediction, and recommendation tasks.
Graphs are ubiquitous in modelling relational structures. Recent endeavours in machine learning for graph-structured data have led to many architectures and learning algorithms. However, the graph used by these algorithms is often constructed based on inaccurate modelling assumptions and/or noisy data. As a result, it fails to represent the true relationships between nodes. A Bayesian framework which targets posterior inference of the graph by considering it as a random quantity can be beneficial. In this paper, we propose a novel non-parametric graph model for constructing the posterior distribution of graph adjacency matrices. The proposed model is flexible in the sense that it can effectively take into account the output of graph-based learning algorithms that target specific tasks. In addition, model inference scales well to large graphs. We demonstrate the advantages of this model in three different problem settings: node classification, link prediction and recommendation.