Training Stable Graph Neural Networks Through Constrained Learning

TL;DR

This paper introduces a constrained learning method for Graph Neural Networks that enhances stability of representations under graph perturbations without sacrificing predictive accuracy.

Contribution

It proposes a novel stability-constrained training framework for GNNs, improving robustness while maintaining accuracy.

Findings

More stable representations achieved in real-world data

Stability constraints do not reduce overall prediction accuracy

Framework applicable to various graph perturbations

Abstract

Graph Neural Networks (GNN) rely on graph convolutions to learn features from network data. GNNs are stable to different types of perturbations of the underlying graph, a property that they inherit from graph filters. In this paper we leverage the stability property of GNNs as a typing point in order to seek for representations that are stable within a distribution. We propose a novel constrained learning approach by imposing a constraint on the stability condition of the GNN within a perturbation of choice. We showcase our framework in real world data, corroborating that we are able to obtain more stable representations while not compromising the overall accuracy of the predictor.