| 摘要: |
| 社交网络链路预测旨在分析现有的网络信息来推断未来的链接情况. 这是一个极具挑战性的任务, 因为社交网络具有复杂的时空耦合特征, 表现为时间维度上的动态演化(即时间依赖性)和空间维度上的关联互耦(即空间依赖性). 现有方法主要集中在时域和空域建模上, 没有充分利用图快照序列数据的频域信息. 提出一种新的时频感知图卷积网络(time-frequency-aware graph convolutional network, TFAGCN)用于社交网络链路预测. TFAGCN的主要优点是在统一的网络框架中集成频域、时域和空域信息, 同时捕获社交网络数据中的全局时间依赖关系和局部时空依赖关系. 具体来说, TFAGCN引入频域模块与时空模块: 在频域模块中, 使用快速傅里叶变换完成图快照序列的域转换, 并在频域通过多层感知器学习频率分量的实部和虚部以捕获社交网络全局依赖关系; 在时空模块中, 联合图卷积神经网络和门控循环单元网络分别探索单个图快照的局部拓扑特征和局部时间特征. 同时, 设计先进的时频双向交叉注意力网络, 能够自适应地融合频域特征与时域特征. 此外, 为了有效应对大规模社交网络的链路预测问题, 给出TFAGCN的简化版本——TFAGS. 在6个真实社交网络数据集上进行一系列有说服力的实验验证, 结果显示所设计的时频感知图卷积网络获得了比先进的基线算法更优的链路预测表现, 证实其是一种高效的处理社交网络蕴含信息表达问题的新工具. TFAGCN的代码可在公开的软件项目托管平台中获取: https://github.com/junlonglai/TFAGCN. |
| 关键词: 动态图神经网络 社交网络 链路预测 图学习 多域特征融合学习 |
| DOI：10.13328/j.cnki.jos.007535 |
| 分类号:TP183 |
| 基金项目:广东省自然科学基金面上项目(2023A1515011667); 广东省基础与应用基础研究基金粤深联合基金重点项目(2023B1515120020); 深圳市科技重大专项(KJZD20230923114809020) |
|
| Time-frequency-aware Graph Convolutional Network for Social Network Link Prediction |
|
HE Yu-Lin1,2, LAI Jun-Long2, CHANG Jia-Le1,2, CUI Lai-Zhong2, HUANG Zhe-Xue1,2
|
|
1.Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen), Shenzhen 518107, China;2.College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
|
| Abstract: |
| Social network link prediction aims to analyze existing network information to infer future links. This is a highly challenging task because social networks exhibit complex spatio-temporal coupling, characterized by dynamic evolution over time (i.e., temporal dependency) and interdependent correlations across space (i.e., spatial dependency). Existing methods mainly focus on time-domain and space-domain modeling and do not fully utilize the frequency-domain information of graph snapshot sequence data. This study proposes a time-frequency-aware graph convolutional network (TFAGCN) for social network link prediction. The main advantage of TFAGCN is that frequency-, time-, and space-domain information is integrated together in a unified network framework, which captures both global temporal dependencies and local spatio-temporal dependencies in social network data. Specifically, this study introduces a frequency-domain module and a spatio-temporal module. In the frequency-domain module, the fast Fourier transform is used to transform the graph snapshot sequence, and the multilayer perceptron is used to learn the real and imaginary parts of the frequency components in the frequency domain to capture the global dependencies of social networks. In the spatio-temporal module, a graph convolutional neural network and a gated recurrent unit network are jointly used to explore the local topological features and local temporal features of individual graph snapshots, respectively. In addition, a time-frequency bidirectional cross-attention network is designed to adaptively fuse frequency-domain features with time-domain features. To address link prediction for large-scale social networks, a simplified version of TFAGCN, namely TFAGS, is designed. Extensive experiments conducted on six real-world social network datasets show that the proposed method outperforms state-of-the-art baseline methods in link prediction, thus confirming its effectiveness as an efficient new tool for social network information representation. The code of TFAGCN is available in this repository: https://github.com/junlonglai/TFAGCN. |
| Key words: dynamic graph neural network social network link prediction graph learning multi-domain feature fusion learning |
