SpaceE: Knowledge Graph Embedding by Relational Linear Transformation in the Entity Space
This work addresses a limitation in knowledge graph embedding for AI applications involving complex relational data, though it is incremental as it builds on existing translation distance-based methods.
The paper tackles the problem of modeling non-injective relations in knowledge graphs, which existing translation distance-based methods like TransE and RotatE cannot handle well, by proposing SpaceE, a method that models relations as linear transformations and achieves substantial performance improvements in link prediction, especially on datasets with many non-injective relations.
Translation distance based knowledge graph embedding (KGE) methods, such as TransE and RotatE, model the relation in knowledge graphs as translation or rotation in the vector space. Both translation and rotation are injective; that is, the translation or rotation of different vectors results in different results. In knowledge graphs, different entities may have a relation with the same entity; for example, many actors starred in one movie. Such a non-injective relation pattern cannot be well modeled by the translation or rotation operations in existing translation distance based KGE methods. To tackle the challenge, we propose a translation distance-based KGE method called SpaceE to model relations as linear transformations. The proposed SpaceE embeds both entities and relations in knowledge graphs as matrices and SpaceE naturally models non-injective relations with singular linear transformations. We theoretically demonstrate that SpaceE is a fully expressive model with the ability to infer multiple desired relation patterns, including symmetry, skew-symmetry, inversion, Abelian composition, and non-Abelian composition. Experimental results on link prediction datasets illustrate that SpaceE substantially outperforms many previous translation distance based knowledge graph embedding methods, especially on datasets with many non-injective relations. The code is available based on the PaddlePaddle deep learning platform https://www.paddlepaddle.org.cn.