Knowledge graph embedding (KGE) models achieved state-of-the-art results on many knowledge graph tasks including link prediction and information retrieval. Despite the superior performance of KGE models in practice, we discover a deficiency in the expressiveness of some popular existing KGE models called \emph{Z-paradox}. Motivated by the existence of Z-paradox, we propose a new KGE model called \emph{MQuinE} that does not suffer from Z-paradox while preserves strong expressiveness to model various relation patterns including symmetric/asymmetric, inverse, 1-N/N-1/N-N, and composition relations with theoretical justification. Experiments on real-world knowledge bases indicate that Z-paradox indeed degrades the performance of existing KGE models, and can cause more than 20\% accuracy drop on some challenging test samples. Our experiments further demonstrate that MQuinE can mitigate the negative impact of Z-paradox and outperform existing KGE models by a visible margin on link prediction tasks.

翻译：知识图谱嵌入（KGE）模型在包括链接预测和信息检索在内的多项知识图谱任务上取得了最先进的结果。尽管KGE模型在实践中表现出卓越的性能，但我们发现一些流行的现有KGE模型在表达能力上存在缺陷，称为“Z悖论”。受Z悖论存在的启发，我们提出了一种新的KGE模型——MQuinE，该模型在避免Z悖论的同时，保持了强大的表达能力，能够建模包括对称/非对称关系、逆关系、1-N/N-1/N-N关系及组合关系在内的多种关系模式，并具有理论证明。在真实知识库上的实验表明，Z悖论确实会降低现有KGE模型的性能，并在某些具有挑战性的测试样本上导致超过20%的准确率下降。我们的实验进一步证明，MQuinE能够缓解Z悖论的负面影响，并在链接预测任务上以显著优势超越现有KGE模型。