Graph Pooling with Node Proximity for Hierarchical Representation Learning

TL;DR

This paper introduces a novel graph pooling method that uses node proximity based on topology and features, enabling more effective hierarchical graph representations without complex computations.

Contribution

The proposed pooling strategy leverages node proximity with a structure-aware kernel, improving hierarchical learning and achieving state-of-the-art results.

Findings

Achieves state-of-the-art performance on graph classification benchmarks.

Efficiently exploits graph geometry without explicit eigendecomposition.

Improves hierarchical representation learning in graph neural networks.

Abstract

Graph neural networks have attracted wide attentions to enable representation learning of graph data in recent works. In complement to graph convolution operators, graph pooling is crucial for extracting hierarchical representation of graph data. However, most recent graph pooling methods still fail to efficiently exploit the geometry of graph data. In this paper, we propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Node proximity is obtained by harmonizing the kernel representation of topology information and node features. Implicit structure-aware kernel representation of topology information allows efficient graph pooling without explicit eigendecomposition of the graph Laplacian. Similarities of node signals are adaptively evaluated with the combination of the affine transformation and kernel trick using the Gaussian RBF function. Experimental results demonstrate that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.