Modeling Co-Evolution of Attributed and Structural Information in Graph Sequence
Modeling Co-Evolution of Attributed and Structural Information in Graph Sequence
复制标题
DOI：
10.1109/tkde.2021.3094332
复制
发表时间：
2023-02
影响因子：
8.9
通讯作者：
Daheng Wang;Zhihan Zhang;Yihong Ma;Tong Zhao;Tianwen Jiang;N. Chawla;Meng Jiang
中科院分区：
文献类型：
--
作者：
Daheng Wang;Zhihan Zhang;Yihong Ma;Tong Zhao;Tianwen Jiang;N. Chawla;Meng Jiang
大多数图神经网络模型学习静态属性图中节点的嵌入，以进行预测分析。最近已经进行了学习节点的时间邻近性的尝试。我们发现，真实的动态属性图表现出节点属性和图结构之间复杂的协同进化现象。学习节点嵌入以预测节点属性的变化和图结构随时间的演变仍然是一个悬而未决的问题。在这项工作中，我们提出了一个新的框架CoEvoGNN来建模动态属性图序列。它通过在属性图序列中嵌入生成来保留早期图对当前图的影响。它有一个时间自我注意体系结构来模拟进化中的长期依赖关系。此外，CoEvoGNN还针对属性推理和链接预测这两个动态任务联合优化模型参数。因此，该模型能够捕捉属性变化和链接形成的协同进化模式。该框架可以适用于任何图神经算法，因此我们实现并研究了基于它的三种方法：CoEvoGCN、CoEvoGAT和CoEvoSAGE。实验表明，该框架(及其方法)在预测动态社交图和金融图中的个人属性和人际关系的整个不可见图快照方面优于强大的基线方法。
Most graph neural network models learn embeddings of nodes in static attributed graphs for predictive analysis. Recent attempts have been made to learn temporal proximity of the nodes. We find that real dynamic attributed graphs exhibit complex phenomenon of co-evolution between node attributes and graph structure. Learning node embeddings for forecasting change of node attributes and evolution of graph structure over time remains an open problem. In this work, we present a novel framework called CoEvoGNN for modeling dynamic attributed graph sequence. It preserves the impact of earlier graphs on the current graph by embedding generation through the sequence of attributed graphs. It has a temporal self-attention architecture to model long-range dependencies in the evolution. Moreover, CoEvoGNN optimizes model parameters jointly on two dynamic tasks, attribute inference and link prediction over time. So the model can capture the co-evolutionary patterns of attribute change and link formation. This framework can adapt to any graph neural algorithms so we implemented and investigated three methods based on it: CoEvoGCN, CoEvoGAT, and CoEvoSAGE. Experiments demonstrate the framework (and its methods) outperforms strong baseline methods on predicting an entire unseen graph snapshot of personal attributes and interpersonal links in dynamic social graphs and financial graphs.