[论文解读] CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning

Di Jin, Luzhi Wang+5 more|arXiv (Cornell University)|May 30, 2022

Advanced Graph Neural Networks被引用 4

一句话总结

本文提出CGMN，一种用于自监督图相似性学习的对比图匹配网络，通过利用跨视图和跨图交互来提升节点表征学习。通过生成增强视图并联合优化节点级与图级表征，CGMN在图相似性任务上实现了最先进性能，在Aids700nef和BSD等多个基准数据集上优于现有的无监督与有监督方法。

ABSTRACT

Graph similarity learning refers to calculating the similarity score between two graphs, which is required in many realistic applications, such as visual tracking, graph classification, and collaborative filtering. As most of the existing graph neural networks yield effective graph representations of a single graph, little effort has been made for jointly learning two graph representations and calculating their similarity score. In addition, existing unsupervised graph similarity learning methods are mainly clustering-based, which ignores the valuable information embodied in graph pairs. To this end, we propose a contrastive graph matching network (CGMN) for self-supervised graph similarity learning in order to calculate the similarity between any two input graph objects. Specifically, we generate two augmented views for each graph in a pair respectively. Then, we employ two strategies, namely cross-view interaction and cross-graph interaction, for effective node representation learning. The former is resorted to strengthen the consistency of node representations in two views. The latter is utilized to identify node differences between different graphs. Finally, we transform node representations into graph-level representations via pooling operations for graph similarity computation. We have evaluated CGMN on eight real-world datasets, and the experiment results show that the proposed new approach is superior to the state-of-the-art methods in graph similarity learning downstream tasks.

研究动机与目标

• 为解决联合图表征学习与相似性评分缺乏自监督方法的问题。
• 克服基于聚类的无监督方法忽略跨图节点匹配且需手动选择聚类数量的局限性。
• 设计一种对比学习框架，以增强在增强视图间的一致性节点表征，并捕捉图间差异。
• 在不依赖昂贵真实标签的前提下，实现高性能的图相似性预测。

提出的方法

• CGMN采用孪生GNN架构来处理成对中的两幅图。
• 为每幅图生成两个增强视图，以提供对比学习的多样化上下文。
• 通过跨视图交互，强制同一图的两个视图之间节点表征保持一致。
• 通过跨图交互，实现不同图中对应节点之间的节点级匹配，以捕捉结构与特征差异。
• 通过在优化后的节点嵌入上执行池化操作，获得图级表征，用于最终的相似性计算。
• 采用对比损失进行端到端训练，以最大化正样本图对之间的一致性，同时最小化负样本图对之间的一致性。

实验结果

研究问题

• RQ1 自监督框架是否能有效学习图相似性，而无需依赖标注的相似性分数？
• RQ2 跨视图与跨图交互如何促进节点与图表征学习的改进？
• RQ3 所提出的对比学习策略是否在图相似性任务中优于基于聚类的无监督方法？
• RQ4 模型性能对超参数（如特征掩码和边移除概率）的敏感性如何，尤其是在增强过程中？

主要发现

• 在Aids700nef数据集上，CGMN的MSE为6.641×10⁻³，相比次优方法相对提升达24.13%。
• 在Linux1000数据集上，CGMN相比有监督模型将MSE降低12.28%，相比无监督基线模型降低21.67%。
• 在BSD任务中，CGMN在全部六个数据集中均取得最高AUC分数，结果持续优于现有无监督方法。
• 消融研究证实，若移除任一跨视图或跨图交互模块，性能均出现显著下降，验证了两个组件的必要性。
• 超参数敏感性分析表明，过度增强（如特征掩码或边移除超过10%）会导致性能下降，原因在于结构失真。
• 该模型在未见测试图上泛化能力良好，展示了在图相似性预测任务中的强大零样本迁移能力。