Graph Pooling via Coarsened Graph Infomax

TL;DR

This paper introduces CGIPool, a novel graph pooling method that maximizes mutual information to better preserve global dependencies in hierarchical graph representations, outperforming existing methods.

Contribution

The paper proposes a new graph pooling technique using mutual information maximization and contrastive learning, addressing computational complexity and dependency capture issues.

Findings

CGIPool outperforms state-of-the-art methods on seven datasets.

The method effectively preserves global graph dependencies.

Contrastive learning enhances pooling quality.

Abstract

Graph pooling that summaries the information in a large graph into a compact form is essential in hierarchical graph representation learning. Existing graph pooling methods either suffer from high computational complexity or cannot capture the global dependencies between graphs before and after pooling. To address the problems of existing graph pooling methods, we propose Coarsened Graph Infomax Pooling (CGIPool) that maximizes the mutual information between the input and the coarsened graph of each pooling layer to preserve graph-level dependencies. To achieve mutual information neural maximization, we apply contrastive learning and propose a self-attention-based algorithm for learning positive and negative samples. Extensive experimental results on seven datasets illustrate the superiority of CGIPool comparing to the state-of-the-art methods.