On The Expressive Power of Knowledge Graph Embedding Methods
This work addresses limitations in reasoning abilities for researchers and practitioners using KGE methods, but it is incremental as it builds on existing methods.
The authors tackled the problem of comparing reasoning abilities of Knowledge Graph Embedding (KGE) methods by proposing a mathematical framework, and they introduced a new method, STransCoRe, which improves upon STransE by reducing space complexity.
Knowledge Graph Embedding (KGE) is a popular approach, which aims to represent entities and relations of a knowledge graph in latent spaces. Their representations are known as embeddings. To measure the plausibility of triplets, score functions are defined over embedding spaces. Despite wide dissemination of KGE in various tasks, KGE methods have limitations in reasoning abilities. In this paper we propose a mathematical framework to compare reasoning abilities of KGE methods. We show that STransE has a higher capability than TransComplEx, and then present new STransCoRe method, which improves the STransE by combining it with the TransCoRe insights, which can reduce the STransE space complexity.