Structure-Aware Hierarchical Graph Pooling using Information Bottleneck

TL;DR

This paper introduces HIBPool, a graph pooling method that uses the Information Bottleneck principle and a structure-aware readout to improve graph classification accuracy and robustness against attacks.

Contribution

The paper proposes a novel structure-aware hierarchical pooling method using the IB principle, enhancing expressiveness and robustness in GNNs.

Findings

Outperforms state-of-the-art pooling methods on multiple benchmarks

More resilient to feature-perturbation adversarial attacks

Effectively captures local subgraph structures

Abstract

Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks. For these tasks, different pooling strategies have been proposed to generate a graph-level representation by downsampling and summarizing nodes' features in a graph. However, most existing pooling methods are unable to capture distinguishable structural information effectively. Besides, they are prone to adversarial attacks. In this work, we propose a novel pooling method named as {HIBPool} where we leverage the Information Bottleneck (IB) principle that optimally balances the expressiveness and robustness of a model to learn representations of input data. Furthermore, we introduce a novel structure-aware Discriminative Pooling Readout ({DiP-Readout}) function to capture the informative local subgraph structures in the graph. Finally, our experimental results show that our model significantly outperforms other state-of-art methods on several graph classification benchmarks and more resilient to feature-perturbation attack than existing pooling methods.