SPGP: Structure Prototype Guided Graph Pooling

TL;DR

This paper introduces SPGP, a graph pooling method that leverages prior structural information via learnable prototypes to improve graph classification accuracy and scalability.

Contribution

SPGP is the first pooling method to incorporate explicit structural information through learnable prototypes, enhancing node selection and graph representation.

Findings

SPGP outperforms existing pooling methods on benchmark datasets.

SPGP improves both accuracy and scalability in graph classification.

Learnable prototypes effectively encode structural information.

Abstract

While graph neural networks (GNNs) have been successful for node classification tasks and link prediction tasks in graph, learning graph-level representations still remains a challenge. For the graph-level representation, it is important to learn both representation of neighboring nodes, i.e., aggregation, and graph structural information. A number of graph pooling methods have been developed for this goal. However, most of the existing pooling methods utilize k-hop neighborhood without considering explicit structural information in a graph. In this paper, we propose Structure Prototype Guided Pooling (SPGP) that utilizes prior graph structures to overcome the limitation. SPGP formulates graph structures as learnable prototype vectors and computes the affinity between nodes and prototype vectors. This leads to a novel node scoring scheme that prioritizes informative nodes while encapsulating the useful structures of the graph. Our experimental results show that SPGP outperforms state-of-the-art graph pooling methods on graph classification benchmark datasets in both accuracy and scalability.