Fan Shiqi, Fan Guoxi, Nie Hongyi, Yao Quanming, Liu Yang, Li Xuelong, Wang Zhen
IEEE Trans Neural Netw Learn Syst. 2025 Apr;36(4):7487-7499. doi: 10.1109/TNNLS.2024.3406869. Epub 2025 Apr 4.
Reasoning over temporal knowledge graphs (TKGs) is a challenging task that requires models to infer future events based on past facts. Currently, subgraph-based methods have become the state-of-the-art (SOTA) techniques for this task due to their superior capability to explore local information in knowledge graphs (KGs). However, while previous methods have been effective in capturing semantic patterns in TKG, they are hard to capture more complex topological patterns. In contrast, path-based methods can efficiently capture relation paths between nodes and obtain relation patterns based on the order of relation connections. But subgraphs can retain much more information than a single path. Motivated by this observation, we propose a new subgraph-based approach to capture complex relational patterns. The method constructs candidate-oriented relational graphs to capture the local structure of TKGs and introduces a variant of a graph neural network model to learn the graph structure information between query-candidate pairs. In particular, we first design a prior directed temporal edge sampling method, which is starting from the query node and generating multiple candidate-oriented relational graphs simultaneously. Next, we propose a recursive propagation architecture that can encode all relational graphs in the local structures in parallel. Additionally, we introduce a self-attention mechanism in the propagation architecture to capture the query's preference. Finally, we design a simple scoring function to calculate the candidate nodes' scores and generate the model's predictions. To validate our approach, we conduct extensive experiments on four benchmark datasets (ICEWS14, ICEWS18, ICEWS0515, and YAGO). Experiments on four benchmark datasets demonstrate that our proposed approach possesses stronger inference and faster convergence than the SOTA methods. In addition, our method provides a relational graph for each query-candidate pair, which offers interpretable evidence for TKG prediction results.
基于时间知识图谱（TKGs）进行推理是一项具有挑战性的任务，它要求模型根据过去的事实推断未来事件。目前，基于子图的方法因其在知识图谱（KGs）中探索局部信息的卓越能力，已成为该任务的当前最优（SOTA）技术。然而，尽管先前的方法在捕捉TKG中的语义模式方面很有效，但它们很难捕捉更复杂的拓扑模式。相比之下，基于路径的方法可以有效地捕捉节点之间的关系路径，并根据关系连接的顺序获得关系模式。但是子图能够保留比单一路径多得多的信息。受此观察启发，我们提出一种新的基于子图的方法来捕捉复杂的关系模式。该方法构建面向候选的关系图以捕捉TKG的局部结构，并引入图神经网络模型的一个变体来学习查询 - 候选对之间的图结构信息。具体而言，我们首先设计一种先验有向时间边采样方法，该方法从查询节点开始并同时生成多个面向候选的关系图。接下来，我们提出一种递归传播架构，它可以并行编码局部结构中的所有关系图。此外，我们在传播架构中引入自注意力机制以捕捉查询的偏好。最后，我们设计一个简单的评分函数来计算候选节点的分数并生成模型的预测。为了验证我们的方法，我们在四个基准数据集（ICEWS14、ICEWS18、ICEWS0515和YAGO）上进行了广泛的实验。在四个基准数据集上的实验表明，我们提出的方法比SOTA方法具有更强的推理能力和更快的收敛速度。此外，我们的方法为每个查询 - 候选对提供一个关系图，这为TKG预测结果提供了可解释的证据。
