Relational VAE: A Continuous Latent Variable Model for Graph Structured Data

Charilaos Mylonas, Imad Abdallah, Eleni Chatzi

Keywords: Graph Neural Networks, Variational Inference, Stochastic Gradient Variational Bayes, Wind Farms, Neural Processes

TL;DR: A Variational Bayes approach to probabilistic modeling for directed attributed graph data.

Abstract: Graph Networks (GNs) enable the fusion of prior knowledge and relational reasoning with flexible function approximations. In this work, a general GN-based model is proposed which takes full advantage of the relational modeling capabilities of GNs and extends these to probabilistic modeling with Variational Bayes (VB). To that end, we combine complementary pre-existing approaches on VB for graph data and propose an approach that relies on graph-structured latent and conditioning variables. It is demonstrated that Neural Processes can also be viewed through the lens of the proposed model. We show applications on the problem of structured probability density modeling for simulated and real wind farm monitoring data, as well as on the meta-learning of simulated Gaussian Process data. We release the source code, along with the simulated datasets.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/relational-vae-a-continuous-latent-variable/code)