Recent work on knowledge graph completion (KGC) focused on learning embeddings of entities and relations in knowledge graphs. These embedding methods require that all test entities are observed at training time, resulting in a time-consuming retraining process for out-of-knowledge-graph (OOKG) entities. To address this issue, current inductive knowledge embedding methods employ graph neural networks (GNNs) to represent unseen entities by aggregating information of known neighbors. They face three important challenges: (i) data sparsity, (ii) the presence of complex patterns in knowledge graphs (e.g., inter-rule correlations), and (iii) the presence of interactions among rule mining, rule inference, and embedding. In this paper, we propose a virtual neighbor network with inter-rule correlations (VNC) that consists of three stages: (i) rule mining, (ii) rule inference, and (iii) embedding. In the rule mining process, to identify complex patterns in knowledge graphs, both logic rules and inter-rule correlations are extracted from knowledge graphs based on operations over relation embeddings. To reduce data sparsity, virtual neighbors for OOKG entities are predicted and assigned soft labels by optimizing a rule-constrained problem. We also devise an iterative framework to capture the underlying relations between rule learning and embedding learning. In our experiments, results on both link prediction and triple classification tasks show that the proposed VNC framework achieves state-of-the-art performance on four widely-used knowledge graphs. Further analysis reveals that VNC is robust to the proportion of unseen entities and effectively mitigates data sparsity.

翻译：知识图谱补全（KGC）近期研究聚焦于学习知识图谱中实体与关系的嵌入表示。这些嵌入方法要求所有测试实体在训练阶段均被观测到，导致处理知识图谱外（OOKG）实体时需进行耗时的重新训练。为解决此问题，当前归纳式知识嵌入方法采用图神经网络（GNN）通过聚合已知邻居信息来表征未见实体，但面临三大关键挑战：（i）数据稀疏性，（ii）知识图谱中的复杂模式（如规则间相关性），以及（iii）规则挖掘、规则推理与嵌入之间的相互作用。本文提出一种具有规则间相关性的虚拟邻居网络（VNC），包含三个阶段：（i）规则挖掘，（ii）规则推理，（iii）嵌入表示。在规则挖掘过程中，为识别知识图谱中的复杂模式，基于关系嵌入的运算操作从知识图谱中提取逻辑规则与规则间相关性。为缓解数据稀疏性，通过优化规则约束问题为OOKG实体预测虚拟邻居并分配软标签。我们还设计了一种迭代框架以捕捉规则学习与嵌入学习之间的潜在关联。实验结果表明，在链路预测与三元组分类任务中，所提出的VNC框架在四个广泛使用的知识图谱上均取得了最优性能。进一步分析表明，VNC对未见实体比例具有鲁棒性，并能有效缓解数据稀疏问题。