Revisiting Robustness in Graph Machine Learning

TL;DR

This paper introduces a semantics-aware notion of adversarial graphs in GNNs, revealing that many perturbations violate semantic content, yet GNNs are generally over-robust, and incorporating label-structure improves robustness and accuracy.

Contribution

It proposes a new semantics-aware framework for evaluating GNN robustness, demonstrating that existing perturbations often alter semantics and that label-structure integration enhances robustness and test performance.

Findings

Most perturbations violate semantic content assumptions.

GNNs exhibit over-robustness beyond semantic change.

Including label-structure reduces over-robustness and improves accuracy.

Abstract

Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the studied perturbations always preserve a core assumption of adversarial examples: that of unchanged semantic content. To address this problem, we introduce a more principled notion of an adversarial graph, which is aware of semantic content change. Using Contextual Stochastic Block Models (CSBMs) and real-world graphs, our results uncover: $i)$ for a majority of nodes the prevalent perturbation models include a large fraction of perturbed graphs violating the unchanged semantics assumption; $ii)$ surprisingly, all assessed GNNs show over-robustness - that is robustness beyond the point of semantic change. We find this to be a complementary phenomenon to adversarial examples and show that including the label-structure of the training graph into the inference process of GNNs significantly reduces over-robustness, while having a positive effect on test accuracy and adversarial robustness. Theoretically, leveraging our new semantics-aware notion of robustness, we prove that there is no robustness-accuracy tradeoff for inductively classifying a newly added node.