提出GNN与Transformer协作架构，提升图对比学习的可靠性。
GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning
- 融合GNN与Transformer，利用图结构生成更全面表示
- 理论分析验证方法可信性，实验达当前最优性能
- 适合关注图表示学习可靠性的研究者参考
图对比学习（GCL）已成为图表示学习领域的热点。与依赖大量标签的传统监督学习不同，GCL通过数据增强生成多视图及正负样本对，其性能受增强策略影响显著。然而，常用随机增强可能破坏图的潜在语义。此外，传统图神经网络（GNN）在GCL中普遍存在过平滑和过挤压问题。为此，本文提出可信图对比学习的GNN-Transformer协作架构（GTCA），融合两者优势，引入图拓扑信息以获取更全面的图表示。理论分析验证了方法的可信性。在基准数据集上的大量实验表明，该方法达到领先水平的实证性能。
原文摘要 · Abstract (English)
Graph contrastive learning (GCL) has become a hot topic in the field of graph representation learning. In contrast to traditional supervised learning relying on a large number of labels, GCL exploits augmentation strategies to generate multiple views and positive/negative pairs, both of which greatly influence the performance. Unfortunately, commonly used random augmentations may disturb the underlying semantics of graphs. Moreover, traditional GNNs, a type of widely employed encoders in GCL, are inevitably confronted with over-smoothing and over-squashing problems. To address these issues, we propose GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning (GTCA), which inherits the advantages of both GNN and Transformer, incorporating graph topology to obtain comprehensive graph representations. Theoretical analysis verifies the trustworthiness of the proposed method. Extensive experiments on benchmark datasets demonstrate state-of-the-art empirical performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。