Knowledge graph embedding (KGE) focuses on representing the entities and relations of a knowledge graph (KG) into the continuous vector spaces, which can be employed to predict the missing triples to achieve knowledge graph completion (KGC). However, KGE models often only briefly learn structural correlations of triple data and embeddings would be misled by the trivial patterns and noisy links in real-world KGs. To address this issue, we build the new paradigm of KGE in the context of causality and embedding disentanglement. We further propose a Causality-enhanced knowledge graph Embedding (CausE) framework. CausE employs causal intervention to estimate the causal effect of the confounder embeddings and design new training objectives to make stable predictions. Experimental results demonstrate that CausE could outperform the baseline models and achieve state-of-the-art KGC performance. We release our code in https://github.com/zjukg/CausE.

翻译：知识图谱嵌入（KGE）专注于将知识图谱（KG）中的实体和关系表示为连续向量空间，从而可用于预测缺失的三元组以实现知识图谱补全（KGC）。然而，KGE模型通常仅粗略学习三元组数据的结构相关性，其嵌入结果易受现实世界KG中的琐碎模式和噪声链接误导。为解决此问题，我们将KGE的新范式建立在因果关系与嵌入解耦的语境中，并进一步提出因果增强的知识图谱嵌入（CausE）框架。CausE通过因果干预估计混杂嵌入的因果效应，设计新的训练目标以实现稳定预测。实验结果表明，CausE能够超越基线模型并达到最先进的KGC性能。我们已将代码开源至https://github.com/zjukg/CausE。