Motif-driven Subgraph Structure Learning for Graph Classification

TL;DR

This paper introduces MOSGSL, a novel method that leverages motif-driven subgraph structure learning to enhance graph classification performance by adaptively selecting and optimizing key subgraphs.

Contribution

The paper proposes a new subgraph structure learning approach guided by motifs, specifically designed for graph classification, addressing the lack of subgraph-level guidance in existing GSL methods.

Findings

Significant improvement over baseline methods in graph classification tasks

Effective subgraph selection and structure optimization demonstrated

Flexible and generalizable across different backbones and learning procedures

Abstract

To mitigate the suboptimal nature of graph structure, Graph Structure Learning (GSL) has emerged as a promising approach to improve graph structure and boost performance in downstream tasks. Despite the proposal of numerous GSL methods, the progresses in this field mostly concentrated on node-level tasks, while graph-level tasks (e.g., graph classification) remain largely unexplored. Notably, applying node-level GSL to graph classification is non-trivial due to the lack of find-grained guidance for intricate structure learning. Inspired by the vital role of subgraph in graph classification, in this paper we explore the potential of subgraph structure learning for graph classification by tackling the challenges of key subgraph selection and structure optimization. We propose a novel Motif-driven Subgraph Structure Learning method for Graph Classification (MOSGSL). Specifically, MOSGSL incorporates a subgraph structure learning module which can adaptively select important subgraphs. A motif-driven structure guidance module is further introduced to capture key subgraph-level structural patterns (motifs) and facilitate personalized structure learning. Extensive experiments demonstrate a significant and consistent improvement over baselines, as well as its flexibility and generalizability for various backbones and learning procedures.