Distance Metric Learning using Graph Convolutional Networks: Application to Functional Brain Networks

TL;DR

This paper introduces a novel graph distance metric learning approach using graph convolutional networks and spectral graph theory, specifically applied to functional brain networks to improve disorder classification.

Contribution

It presents a new spectral graph convolutional network-based metric learning method tailored for graph similarity evaluation in connectomics.

Findings

Improves graph similarity assessment for brain networks

Enhances classification accuracy by 11.9% on ABIDE dataset

Demonstrates effectiveness in clinical connectomics applications

Abstract

Evaluating similarity between graphs is of major importance in several computer vision and pattern recognition problems, where graph representations are often used to model objects or interactions between elements. The choice of a distance or similarity metric is, however, not trivial and can be highly dependent on the application at hand. In this work, we propose a novel metric learning method to evaluate distance between graphs that leverages the power of convolutional neural networks, while exploiting concepts from spectral graph theory to allow these operations on irregular graphs. We demonstrate the potential of our method in the field of connectomics, where neuronal pathways or functional connections between brain regions are commonly modelled as graphs. In this problem, the definition of an appropriate graph similarity function is critical to unveil patterns of disruptions associated with certain brain disorders. Experimental results on the ABIDE dataset show that our method can learn a graph similarity metric tailored for a clinical application, improving the performance of a simple k-nn classifier by 11.9% compared to a traditional distance metric.