Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (20): 49-67.DOI: 10.3778/j.issn.1002-8331.2403-0308

• Research Hotspots and Reviews • Previous Articles     Next Articles

Survey of Dynamic Graph Neural Network for Link Prediction

ZHANG Qi, CHEN Xu, WANG Shuyang, JING Yongjun, SONG Jifei   

  1. 1.School of Computer Science and Engineering, North Minzu University, Yinchuan 750030, China
    2.School of Electrical and Information Engineering, North Minzu University, Yinchuan 750030, China
    3.National New Internet Exchange Center, Zhongwei, Ningxia 755001, China
  • Online:2024-10-15 Published:2024-10-15

动态图神经网络链接预测综述

张其,陈旭,王叔洋,景永俊,宋吉飞   

  1. 1.北方民族大学 计算机科学与工程学院,银川 750030
    2.北方民族大学 电气信息工程学院,银川 750030
    3.国家新型互联网交换中心,宁夏 中卫 755001

Abstract: Complex dynamic network data, such as social networks, protein interaction networks, and infectious disease transmission networks, are prevalent in the real world, consisting of numerous nodes and edges. Effective mining and utilization of such data for accurate prediction have become a key task. Dynamic graph neural network link prediction is an important branch of deep learning research, which aims to analyze the intrinsic laws of network evolution over time and predict potential future linkages, providing valuable information and basis for decision-making in various fields. This paper first reviews the development of dynamic graph neural networks, then introduces the modeling methods and training processes of dynamic graphs. Based on this, the paper categorizes dynamic graph neural network link prediction models into two main types according to the granularity of time: discrete dynamic graph models and continuous dynamic graph models, and provides an overview of the modeling methods used by current mainstream models in each category. In addition, it also introduces commonly used data sets, evaluation indicators and some application scenarios in dynamic graph link prediction research. Finally, the future development trends in this field are discussed prospectively.

Key words: graph neural network, deep learning, dynamic graph learning, link prediction, temporal graph

摘要: 在现实世界中,复杂的动态网络数据广泛存在,如社交网络、蛋白质相互作用网络和传染病传播网络,它们由大量的节点和边构成。针对这类数据的有效挖掘和利用,以进行精准预测,成为了一项关键任务。动态图神经网络链接预测是深度学习研究领域的一个重要分支,它旨在解析网络随时间演化的内在规律,并预测未来可能形成的链接,为各领域的决策提供有价值的信息和依据。回顾了动态图神经网络的发展历程,介绍动态图的建模方法和训练流程。在此基础上,根据时间粒度的不同,将动态图神经网络链接预测模型细分为离散动态图模型和连续动态图模型两大类,并综述了每一类别中当前主流模型所采用的建模方法;介绍了动态图链接预测研究中常用的数据集、评价指标和应用场景。最后,对该领域的未来发展趋势进行了前瞻性探讨。

关键词: 图神经网络, 深度学习, 动态图学习, 链接预测, 时间图