Towards an Efficient and General Framework of Robust Training for Graph Neural Networks

TL;DR

This paper introduces a scalable and efficient framework for robust training of Graph Neural Networks using greedy search and zeroth-order methods, addressing security and scalability issues of existing approaches.

Contribution

It proposes a novel general framework that enhances robustness of GNNs against adversarial attacks, suitable for large-scale and time-sensitive applications.

Findings

Significantly reduces computational cost compared to existing methods.

Achieves comparable or better robustness against adversarial attacks.

Demonstrates effectiveness on large-scale graph datasets.

Abstract

Graph Neural Networks (GNNs) have made significant advances on several fundamental inference tasks. As a result, there is a surge of interest in using these models for making potentially important decisions in high-regret applications. However, despite GNNs' impressive performance, it has been observed that carefully crafted perturbations on graph structures (or nodes attributes) lead them to make wrong predictions. Presence of these adversarial examples raises serious security concerns. Most of the existing robust GNN design/training methods are only applicable to white-box settings where model parameters are known and gradient based methods can be used by performing convex relaxation of the discrete graph domain. More importantly, these methods are not efficient and scalable which make them infeasible in time sensitive tasks and massive graph datasets. To overcome these limitations, we propose a general framework which leverages the greedy search algorithms and zeroth-order methods to obtain robust GNNs in a generic and an efficient manner. On several applications, we show that the proposed techniques are significantly less computationally expensive and, in some cases, more robust than the state-of-the-art methods making them suitable to large-scale problems which were out of the reach of traditional robust training methods.