Empowering Dual-Level Graph Self-Supervised Pretraining with Motif Discovery
This work addresses problems in graph learning for researchers and practitioners, offering an incremental improvement by combining node-level and subgraph-level tasks with motif discovery.
The paper tackles challenges in self-supervised graph pretraining, such as limited topology learning and human knowledge dependency, by proposing DGPM, a dual-level pretraining method that autonomously discovers motifs and outperforms state-of-the-art methods on 15 datasets in unsupervised representation and transfer learning.
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.