Log In Sign Up

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

by   Charilaos Mylonas, et al.

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.


Deep Mean Functions for Meta-Learning in Gaussian Processes

Fitting machine learning models in the low-data limit is challenging. Th...

A Review of Relational Machine Learning for Knowledge Graphs

Relational machine learning studies methods for the statistical analysis...

Meta Learning with Relational Information for Short Sequences

This paper proposes a new meta-learning method -- named HARMLESS (HAwkes...

Knowledge Generation – Variational Bayes on Knowledge Graphs

This thesis is a proof of concept for the potential of Variational Auto-...

Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models - a Gentle Tutorial

In this tutorial we explain the inference procedures developed for the s...