LAMP：用于异构图的可学习元路径引导对抗对比学习
LAMP: Learnable Meta-Path Guided Adversarial Contrastive Learning for Heterogeneous Graphs
AI总结：
针对无监督异构图对比学习对预定义元路径组合敏感的问题，提出LAMP框架，通过整合多类元路径子图并采用对抗边剪枝与双视图对比学习，在HGB四个数据集上显著提升准确率与鲁棒性。
摘要：
异构图神经网络（HGNN）显著推动了信息检索（IR）领域的发展。尽管如此，HGNN的有效性仍严重依赖高质量标签，而这些标签通常获取成本高昂。这一挑战使关注点转向异构图对比学习（HGCL），该方法通常需要预定义的元路径。然而，我们的研究发现表明，在无监督设置下，元路径组合会显著影响性能，而这一方面在当前文献中常被忽视。现有HGCL方法在不同元路径组合下的结果存在相当大的差异，从而给实现稳定且高性能的优化过程带来挑战。为此，我们提出了LAMP（LearnAble Meta-Path，可学习元路径），这是一种新颖的对抗对比学习方法，利用各元路径子图之间的重叠，将多种元路径子图整合为统一且稳定的结构。为解决该整合子图的稠密问题，我们提出了一种用于边剪枝的对抗训练策略，通过保持稀疏性来提升模型性能与鲁棒性。LAMP旨在最大化元路径视图与网络模式视图之间的差异，以引导对比学习捕获最有意义的信息。我们在来自异构图基准（HGB）的四个不同数据集上开展了大量实验研究，结果表明LAMP在准确率和鲁棒性方面均显著优于现有的最先进无监督模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
