arXiv 2304.100792024-10-02cs.LG

通过边时间状态建模与结构增强 Transformer 进行动态图表示学习

Dynamic Graph Representation Learning via Edge Temporal States Modeling and Structure-reinforced Transformer

School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）；School of Computer Science and Technology, Donghua University（东华大学计算机科学与技术学院）；School of Computer and Information Engineering, Shanghai Polytechnic University（上海第二工业大学计算机与信息工程学院）

Shengxiang Hu, Guobing Zou, Song Yang, Shiyi Lin, Yanglan Gan, Bofeng Zhang

备注：: This work has been submitted to the Elsevier for possible publication

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对动态图中边时间状态影响建模不足及 GNN 过平滑问题，提出 RSGT 框架，结合边状态启发式建模与循环结构增强 Transformer，在四个真实数据集的动态链接预测中取得最优表现。

摘要：

动态图表示学习已成为一个重要研究领域，其推动力来自现实应用中对分析随时间演化的图数据日益增长的需求。尽管近期利用循环神经网络（RNN）和图神经网络（GNN）的方法已展现出良好前景，但它们往往无法充分捕捉时间边状态对节点间关系的影响，因而忽视了由这些不断演化的关系所引发的节点特征动态变化。此外，这些方法还受到 GNN 固有过平滑问题的困扰，该问题阻碍了全局结构特征的提取。为应对这些挑战，我们提出了 Recurrent Structure-reinforced Graph Transformer（RSGT，循环结构增强图 Transformer），这是一种用于动态图表示学习的新颖框架。该框架首先设计了一种启发式方法，根据连续快照之间的差异采用不同的边类型和权重，对边时间状态进行显式建模，从而将不同的边时间状态整合到图的拓扑结构中。随后，我们提出一种结构增强图 Transformer，通过循环学习范式捕捉编码图拓扑与演化动态的时间节点表示，从而能够同时提取局部和全局结构特征。在四个真实世界数据集上的综合实验表明，RSGT 在离散动态图表示学习中具有优越性能，并在动态链接预测任务上持续优于现有方法。

英文摘要：

Dynamic graph representation learning has emerged as a crucial research area, driven by the growing need for analyzing time-evolving graph data in real-world applications. While recent approaches leveraging recurrent neural networks (RNNs) and graph neural networks (GNNs) have shown promise, they often fail to adequately capture the impact of temporal edge states on inter-node relationships, consequently overlooking the dynamic changes in node features induced by these evolving relationships. Furthermore, these methods suffer from GNNs' inherent over-smoothing problem, which hinders the extraction of global structural features. To address these challenges, we introduce the Recurrent Structure-reinforced Graph Transformer (RSGT), a novel framework for dynamic graph representation learning. It first designs a heuristic method to explicitly model edge temporal states by employing different edge types and weights based on the differences between consecutive snapshots, thereby integrating varying edge temporal states into the graph's topological structure. We then propose a structure-reinforced graph transformer that captures temporal node representations encoding both graph topology and evolving dynamics through a recurrent learning paradigm, enabling the extraction of both local and global structural features. Comprehensive experiments on four real-world datasets demonstrate RSGT's superior performance in discrete dynamic graph representation learning, consistently outperforming existing methods in dynamic link prediction tasks.

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。