arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.03449cs.LGcs.SI
收藏

基于时间增强的动态图节点分类

Dynamic Graph Node Classification via Time Augmentation

Visa Research(维萨研究院)

Jiarui Sun, Mengting Gu, Chin-Chia Michael Yeh, Yujie Fan, Girish Chowdhary, Wei Zhang

摘要:

图结构数据的节点分类旨在对标签未知的节点进行分类。虽然静态图的研究是普遍的,很少有研究集中在动态图节点分类。动态图上的节点分类具有挑战性,原因有两个。首先,该模型需要捕获结构和时间信息,特别是在具有悠久历史的动态图上,需要大的感受野。其次,随着动态图的大小增加,模型的可伸缩性成为一个重要的问题。为了解决这些问题,我们提出了时间增强动态图神经网络(TADGNN)框架。TADGNN由两个模块组成:1)时间增强模块,它从结构上捕获节点在时间上的时间演化,创建时间增强的时空图,以及2)信息传播模块,它使用构建的时间增强图来学习每个节点在时间上的动态表示。我们在四个动态图基准上进行节点分类实验。实验结果表明,TADGNN框架优于几个静态和动态国家的最先进的(SOTA)GNN模型,同时表现出优越的可扩展性。我们还进行了理论和实证分析,以验证所提出的方法的效率。我们的代码可在https://sites.google.com/view/tadgnn上获得。

英文摘要:

Node classification for graph-structured data aims to classify nodes whose labels are unknown. While studies on static graphs are prevalent, few studies have focused on dynamic graph node classification. Node classification on dynamic graphs is challenging for two reasons. First, the model needs to capture both structural and temporal information, particularly on dynamic graphs with a long history and require large receptive fields. Second, model scalability becomes a significant concern as the size of the dynamic graph increases. To address these problems, we propose the Time Augmented Dynamic Graph Neural Network (TADGNN) framework. TADGNN consists of two modules: 1) a time augmentation module that captures the temporal evolution of nodes across time structurally, creating a time-augmented spatio-temporal graph, and 2) an information propagation module that learns the dynamic representations for each node across time using the constructed time-augmented graph. We perform node classification experiments on four dynamic graph benchmarks. Experimental results demonstrate that TADGNN framework outperforms several static and dynamic state-of-the-art (SOTA) GNN models while demonstrating superior scalability. We also conduct theoretical and empirical analyses to validate the efficiency of the proposed method. Our code is available at https://sites.google.com/view/tadgnn.

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。

↑