Few-Shot Knowledge Graph Completion


  • Chuxu Zhang University of Notre Dame
  • Huaxiu Yao Pennsylvania State University
  • Chao Huang JD Finance American Corporation
  • Meng Jiang University of Notre Dame
  • Zhenhui Li Pennsylvania State University
  • Nitesh V. Chawla University of Notre Dame




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.




How to Cite

Zhang, C., Yao, H., Huang, C., Jiang, M., Li, Z., & Chawla, N. V. (2020). Few-Shot Knowledge Graph Completion. Proceedings of the AAAI Conference on Artificial Intelligence, 34(03), 3041-3048. https://doi.org/10.1609/aaai.v34i03.5698



AAAI Technical Track: Knowledge Representation and Reasoning