Empowering Dual-Level Graph Self-Supervised Pretraining with Motif Discovery

TL;DR

This paper introduces DGPM, a novel dual-level self-supervised graph pretraining method that autonomously discovers motifs and enhances multi-level interactions, leading to improved performance and interpretability.

Contribution

DGPM is the first to combine dual-level pretraining with autonomous motif discovery and cross-matching for enhanced graph representation learning.

Findings

Outperforms state-of-the-art methods on 15 datasets.

Effectively uncovers meaningful graph motifs.

Enhances robustness and interpretability of graph models.

Abstract

While self-supervised graph pretraining techniques have shown promising results in various domains, their application still experiences challenges of limited topology learning, human knowledge dependency, and incompetent multi-level interactions. To address these issues, we propose a novel solution, Dual-level Graph self-supervised Pretraining with Motif discovery (DGPM), which introduces a unique dual-level pretraining structure that orchestrates node-level and subgraph-level pretext tasks. Unlike prior approaches, DGPM autonomously uncovers significant graph motifs through an edge pooling module, aligning learned motif similarities with graph kernel-based similarities. A cross-matching task enables sophisticated node-motif interactions and novel representation learning. Extensive experiments on 15 datasets validate DGPM's effectiveness and generalizability, outperforming state-of-the-art methods in unsupervised representation learning and transfer learning settings. The autonomously discovered motifs demonstrate the potential of DGPM to enhance robustness and interpretability.