Representation Learning of Large-Scale Knowledge Graphs via Entity Feature Combinations

Abstract

Knowledge graphs are typical large-scale multi-relational struc-tures, which comprise a large amount of fact triplets. Nonethe-less, existing knowledge graphs are still sparse and far from being complete. To refine the knowledge graphs, representation learning is widely used to embed fact triplets into low-dimensional spaces. Many existing knowledge graph embedding models either focus on learning rich features from entities but fail to extract good fea-tures of relations, or employ sophisticated models that have rather high time and memory-space complexities. In this paper, we propose a novel knowledge graph embedding model, CombinE. It exploits entity features from two complemen-tary perspectives via the plus and minus combinations. We start with the plus combination, where we use shared features of entity pairs participating in a relation to convey its relation features. To also allow differences of each pairs of entities participating in a re-lation, we also use the minus combination, where we concentrate on individual entity features, and regard relations as a channel to offset the divergence and preserve the prominence between head and tail entities. Compared with the state-of-the-art models, our experimental results demonstrate that CombinE outperforms ex-isting ones and has low time and memory-space complexities.