Few-Shot Knowledge Graph Completion

Knowledge graphs (KGs) serve as useful resources for various natural language processing applications. Previous KG completion approaches require a large number of training instances (i. e. , head-tail entity pairs) for every relation. The real case is that for most of the relations, very few entity pairs are available. Existing work of one-shot learning limits method generalizability for few-shot scenarios and does not fully use the supervisory information; however, few-shot KG completion has not been well studied yet. In this work, we propose a novel few-shot relation learning model (FSRL) that aims at discovering facts of new relations with few-shot references. FSRL can effectively capture knowledge from heterogeneous graph structure, aggregate representations of few-shot references, and match similar entity pairs of reference set for every relation. Extensive experiments on two public datasets demonstrate that FSRL outperforms the state-of-the-art.

Authors

• Chuxu Zhang Brandeis University, Waltham, MA 02453
• Huaxiu Yao University of North Carolina at Chapel Hill
• Chao Huang Sun Yat-Sen University
• Meng Jiang University of Science and Technology of China
• Zhenhui Li University of Electronic Science and Technology of China
• Nitesh V. Chawla University of Notre Dame

Keywords

No keywords are indexed for this paper.