MQuinE: a cure for "Z-paradox" in knowledge graph embedding models
This addresses a specific expressiveness problem in knowledge graph embeddings for AI applications like link prediction, representing an incremental improvement.
The paper tackles the 'Z-paradox' deficiency in knowledge graph embedding models, which causes over 20% accuracy drop on some test samples, and proposes MQuinE to mitigate this issue, outperforming existing models on link prediction tasks.
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.