# Graph Neural Processes: Towards Bayesian Graph Neural Networks

arXiv: https://arxiv.org/abs/1902.10042 · HTML: https://mlsanity.com/paper/1902.10042/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2019.

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

- [The Neural Process Family: Survey, Applications and Perspectives](https://mlsanity.com/paper/2209.00517/) (2022)
- [Approximately Equivariant Neural Processes](https://mlsanity.com/paper/2406.13488/) (2024)
- [How Neural Processes Improve Graph Link Prediction](https://mlsanity.com/paper/2109.14894/) (2021)
- [Learning Continuous Network Emerging Dynamics from Scarce Observations via Data-Adaptive Stochastic Processes](https://mlsanity.com/paper/2310.16466/) (2023)
- [GraphPPD: Posterior Predictive Modelling for Graph-Level Inference](https://mlsanity.com/paper/2508.16995/) (2025)
- [Amortized Counterfactual Prediction with Graph Neural Networks](https://mlsanity.com/paper/2610.13724/) (2026)

## Abstract (arXiv)

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.