arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.07643cs.LGstat.ML
收藏

基于张量M-积的动态图卷积网络

Dynamic Graph Convolutional Networks Using the Tensor M-Product

University of Colorado Boulder(科罗拉多大学博尔德分校);IBM Research(IBM研究院);Tufts University(塔夫茨大学);Tel Aviv University(特拉维夫大学)

Osman Asif Malik, Shashanka Ubaru, Lior Horesh, Misha E. Kilmer, Haim Avron

摘要:

许多不规则的领域,如社交网络,金融交易,神经元连接,和自然语言结构使用图结构表示。近年来,各种图神经网络(GNN)已成功地应用于此类图的表示学习和预测。在许多现实世界的应用中,底层图随着时间的推移而变化,然而,大多数现有的GNN不足以处理这种动态图。在本文中,我们提出了一种新的技术学习嵌入的动态图使用张量代数框架。我们的方法扩展了流行的图卷积网络(GCN)的学习表示的动态图使用最近提出的张量M-产品技术。理论结果建立了张量方法和张量谱卷积之间的联系。所提出的方法TM-GCN是一致的消息传递神经网络(MPNN)的框架,占空间和时间的消息传递。在真实数据集上的数值实验证明了所提出的方法在动态图上的边缘分类和链接预测任务的性能。我们还考虑了与COVID-19大流行相关的应用,并展示了我们的方法如何用于从接触者追踪数据中早期检测感染者。

英文摘要:

Many irregular domains such as social networks, financial transactions, neuron connections, and natural language constructs are represented using graph structures. In recent years, a variety of graph neural networks (GNNs) have been successfully applied for representation learning and prediction on such graphs. In many of the real-world applications, the underlying graph changes over time, however, most of the existing GNNs are inadequate for handling such dynamic graphs. In this paper we propose a novel technique for learning embeddings of dynamic graphs using a tensor algebra framework. Our method extends the popular graph convolutional network (GCN) for learning representations of dynamic graphs using the recently proposed tensor M-product technique. Theoretical results presented establish a connection between the proposed tensor approach and spectral convolution of tensors. The proposed method TM-GCN is consistent with the Message Passing Neural Network (MPNN) framework, accounting for both spatial and temporal message passing. Numerical experiments on real-world datasets demonstrate the performance of the proposed method for edge classification and link prediction tasks on dynamic graphs. We also consider an application related to the COVID-19 pandemic, and show how our method can be used for early detection of infected individuals from contact tracing data.

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。

↑