Graph Neural Processes: Towards Bayesian Graph Neural Networks

2019/02/26 by Andrew N. Carr, David Wingate, Carr, Andrew +1 · 1 citation
Computer Science · #Advanced Graph Neural Networks #Adversarial Robustness in Machine Learning #Bayesian Modeling and Causal Inference #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1902.10042

openalex publication_date 2019/02/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce Graph Neural Processes (GNP), inspired by the recent work in conditional and latent neural processes. A Graph Neural Process is defined as a Conditional Neural Process that operates on arbitrary graph data. It takes features of sparsely observed context points as input, and outputs a distribution over target points. We demonstrate graph neural processes in edge imputation and discuss benefits and drawbacks of the method for other application areas. One major benefit of GNPs is the ability to quantify uncertainty in deep learning on graph structures. An additional benefit of this method is the ability to extend graph neural networks to inputs of dynamic sized graphs.

Citations

• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric Deep Learning: Going beyond Euclidean data
• Dynamic Graph CNN for Learning on Point Clouds
• Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting
• Conditional Neural Processes
• Graph Neural Networks: A Review of Methods and Applications

Cited by

• GraphPPD: Posterior Predictive Modelling for Graph-Level Inference

Related

• Probability Passing for Graph Neural Networks: Graph Structure and Representations Joint Learning
• Infinite Width Graph Neural Networks for Node Regression/ Classification
• A Practical Tutorial on Graph Neural Networks
• Graph Neural Networks: A Review of Methods and Applications
• Graph neural networks: A review of methods and applications