LAMP: Learnable Meta-Path Guided Adversarial Contrastive Learning for Heterogeneous Graphs
This addresses the challenge of expensive label acquisition for heterogeneous graph neural networks in information retrieval, offering a more stable and effective unsupervised method, though it appears incremental as it builds on existing contrastive learning frameworks.
The paper tackles the problem of performance variability in unsupervised heterogeneous graph contrastive learning due to reliance on pre-defined meta-paths, and introduces LAMP, a learnable meta-path guided adversarial approach that integrates multiple meta-path sub-graphs and uses adversarial training for edge pruning, achieving significant improvements in accuracy and robustness over state-of-the-art models on four HGB datasets.
Heterogeneous graph neural networks (HGNNs) have significantly propelled the information retrieval (IR) field. Still, the effectiveness of HGNNs heavily relies on high-quality labels, which are often expensive to acquire. This challenge has shifted attention towards Heterogeneous Graph Contrastive Learning (HGCL), which usually requires pre-defined meta-paths. However, our findings reveal that meta-path combinations significantly affect performance in unsupervised settings, an aspect often overlooked in current literature. Existing HGCL methods have considerable variability in outcomes across different meta-path combinations, thereby challenging the optimization process to achieve consistent and high performance. In response, we introduce \textsf{LAMP} (\underline{\textbf{L}}earn\underline{\textbf{A}}ble \underline{\textbf{M}}eta-\underline{\textbf{P}}ath), a novel adversarial contrastive learning approach that integrates various meta-path sub-graphs into a unified and stable structure, leveraging the overlap among these sub-graphs. To address the denseness of this integrated sub-graph, we propose an adversarial training strategy for edge pruning, maintaining sparsity to enhance model performance and robustness. \textsf{LAMP} aims to maximize the difference between meta-path and network schema views for guiding contrastive learning to capture the most meaningful information. Our extensive experimental study conducted on four diverse datasets from the Heterogeneous Graph Benchmark (HGB) demonstrates that \textsf{LAMP} significantly outperforms existing state-of-the-art unsupervised models in terms of accuracy and robustness.