Skip to yearly menu bar Skip to main content


Oral
in
Workshop: 2nd ICML Workshop on New Frontiers in Adversarial Machine Learning

Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness

Keywords: [ Adversarial Robustness ] [ Graph Neural Networks ] [ Subgraph Counting ] [ Representation Power ]


Abstract:

We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs). In particular, we use adversarial robustness as a tool to uncover a significant gap between their theoretically possible and empirically achieved expressive power. To do so, we focus on the ability of GNNs to count specific subgraph patterns, which is an established measure of expressivity, and extend the concept of adversarial robustness to this task. Based on this, we develop efficient adversarial attacks for subgraph counting and show that more powerful GNNs fail to generalize even to small perturbations to the graph's structure. Expanding on this, we show that such architectures also fail to count substructures on out-of-distribution graphs.

Chat is not available.