Non-Parametric Graph Learning for Bayesian Graph Neural Networks
arXiv:2006.13335
Abstract
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.
References in corpus (11)
- Inductive Representation Learning on Large Graphs
- BPR: Bayesian Personalized Ranking from Implicit Feedback
- Graph Convolutional Matrix Completion
- Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- Learning Deep Generative Models of Graphs
- NetGAN: Generating Graphs via Random Walks
- Efficient Graph Generation with Graph Recurrent Attention Networks
- Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
- Stochastic Blockmodels meet Graph Neural Networks
- Rethinking Kernel Methods for Node Representation Learning on Graphs