arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.03271cs.LGcs.AI
收藏

局部结构感知的图对比表示学习

Local Structure-aware Graph Contrastive Representation Learning

Yangzhou University(扬州大学);University of Shanghai for Science and Technology(上海理工大学)

Kai Yang, Yuan Liu, Zijuan Zhao, Peijin Ding, Wenqian Zhao

AI总结:

本文提出局部结构感知的图对比表示学习方法LS-GCL,通过构建语义子图并结合局部与全局视角的多级对比学习,在节点分类和链路预测任务上取得优于现有方法的性能。

摘要:

传统图神经网络(GNN)作为一种图表示学习方法,受到标签信息的制约。然而,有效解决标签问题的图对比学习(GCL)方法主要关注全局图的特征信息或小的子图结构(例如一阶邻域)。本文提出了一种局部结构感知的图对比表示学习方法(LS-GCL),从多个视角建模节点的结构信息。具体而言,我们构建了不限于一阶邻居的语义子图。对于局部视角,将每个目标节点的语义子图输入共享的GNN编码器,以获得子图级别的目标节点嵌入。然后,我们使用池化函数生成子图级别的图嵌入。对于全局视角,考虑到原始图保留了节点不可或缺的语义信息,我们利用共享的GNN编码器学习全局图级别的目标节点嵌入。所提出的LS-GCL模型通过多级对比损失函数进行优化,以在三个不同视角上最大化相似实例之间的共同信息。在五个数据集上的实验结果表明,我们的方法在节点分类和链路预测任务上均优于最先进的图表示学习方法。

英文摘要:

Traditional Graph Neural Network (GNN), as a graph representation learning method, is constrained by label information. However, Graph Contrastive Learning (GCL) methods, which tackle the label problem effectively, mainly focus on the feature information of the global graph or small subgraph structure (e.g., the first-order neighborhood). In the paper, we propose a Local Structure-aware Graph Contrastive representation Learning method (LS-GCL) to model the structural information of nodes from multiple views. Specifically, we construct the semantic subgraphs that are not limited to the first-order neighbors. For the local view, the semantic subgraph of each target node is input into a shared GNN encoder to obtain the target node embeddings at the subgraph-level. Then, we use a pooling function to generate the subgraph-level graph embeddings. For the global view, considering the original graph preserves indispensable semantic information of nodes, we leverage the shared GNN encoder to learn the target node embeddings at the global graph-level. The proposed LS-GCL model is optimized to maximize the common information among similar instances at three various perspectives through a multi-level contrastive loss function. Experimental results on five datasets illustrate that our method outperforms state-of-the-art graph representation learning approaches for both node classification and link prediction tasks.

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。

↑