Zhang Dong, Jiang Haoqian, Li Xiaoning, Li Guanyu, Ning Bo, Chen Heng
Information Science and Technology College, Dalian Maritime University, Dalian, 116026, Liaoning, China.
School of Software, Dalian University of Foreign Languages, Dalian, 116026, Liaoning, China.
Neural Netw. 2025 Aug;188:107494. doi: 10.1016/j.neunet.2025.107494. Epub 2025 Apr 24.
Knowledge graphs (KGs) depict entities as nodes and connections as edges, and they are extensively utilized in numerous artificial intelligence applications. However, knowledge graphs often suffer from incompleteness, which seriously affects downstream applications. Knowledge graph embedding (KGE) technology tackles this challenge by encoding entities and relations as vectors, allowing for inference and computations using these representations. Graph convolutional networks (GCNs) are essential knowledge graph embedding technology models. GCN methods capture the topological structure features of the KG by calculating the pair-wise relationships between entities and neighboring nodes. Although GCN models have achieved excellent performance, there are still three main challenges: (1) effectively solving the over-smoothing problem in multi-layer GCN models for knowledge graph representation learning, (2) obtaining high-order information between entities and neighboring nodes beyond the pair-wise relationships, and (3) effectively integrating pair-wise and high-order features of entities. To address these challenges, we proposed an adaptive graph convolutional network model called PHGCN (Pair-wise and High-Order Graph Convolutional Network), which can simultaneously integrate pair-wise and high-order features. PHGCN tackles the three challenges mentioned above in the following ways. (1) We propose a layer-aware GCN to overcome the over-smoothing problem while aggregating pair-wise relationships. (2) We employ simplicial complex neural networks to extract high-order topological features from knowledge graphs. (3) We introduce a self-adaptive aggregation mechanism that effectively integrates pair-wise and high-order features. Our experiments on four benchmark datasets showed that PHGCN outperforms existing methods, achieving state-of-the-art results. The performance improvement from using a simplicial complex neural network to extract high-order features is significant. On the FB15k-237 dataset, PHGCN achieved a 1.5% improvement, while on the WN18RR dataset, it improved by 6.1%.
知识图谱（KGs）将实体表示为节点，将连接表示为边，并且它们在众多人工智能应用中得到了广泛应用。然而，知识图谱常常存在不完整性，这严重影响了下游应用。知识图谱嵌入（KGE）技术通过将实体和关系编码为向量来应对这一挑战，从而允许使用这些表示进行推理和计算。图卷积网络（GCNs）是重要的知识图谱嵌入技术模型。GCN方法通过计算实体与相邻节点之间的成对关系来捕获KG的拓扑结构特征。尽管GCN模型取得了优异的性能，但仍存在三个主要挑战：（1）有效解决用于知识图谱表示学习的多层GCN模型中的过平滑问题；（2）获取实体与相邻节点之间除成对关系之外的高阶信息；（3）有效整合实体的成对和高阶特征。为了应对这些挑战，我们提出了一种名为PHGCN（成对和高阶图卷积网络）的自适应图卷积网络模型，它可以同时整合成对和高阶特征。PHGCN通过以下方式应对上述三个挑战。（1）我们提出了一种层感知GCN，以在聚合成对关系时克服过平滑问题。（2）我们采用单纯复形神经网络从知识图谱中提取高阶拓扑特征。（3）我们引入了一种自适应聚合机制，有效整合成对和高阶特征。我们在四个基准数据集上的实验表明，PHGCN优于现有方法，取得了当前最优的结果。使用单纯复形神经网络提取高阶特征带来的性能提升非常显著。在FB15k - 237数据集上，PHGCN实现了1.5%的提升，而在WN18RR数据集上，提升了6.1%。
