Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion

• Main Authors: Li, Qianyu, Yao, Jiale, Tang, Xiaoli, Yu, Han, Jiang, Siyu, Yang, Haizhi, Song, Hengjie
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Few-Shot Knowledge Graph Completion; Knowledge Graph
• Online Access: https://hdl.handle.net/10356/172789
• Institution: Nanyang Technological University

Few-shot Knowledge Graph Completion (FKGC) has recently attracted significant research interest due to its ability to expand few-shot relation coverage in Knowledge Graphs. Prevailing FKGC approaches focus on exploiting the one-hop neighbor information of entities to enhance few-shot relation embedding. However, these methods select one-hop neighbors randomly and neglect the rich multi-aspect information of entities. Although some methods have attempted to leverage Long Short-Term Memory (LSTM) to learn few-shot relation embedding, they are sensitive to the input order. To address these limitations, we propose the Capsule Neural Tensor Networks with Multi-Aspect Information approach (short for InforMix-FKGC). InforMix-FKGC employs a one-hop neighbor selection strategy based on how valuable they are and encodes multi-aspect information of entities, including one-hop neighbors, attributes and literal description. Then, a capsule network is responsible for integrating the support set and deriving few-shot relation embedding. Moreover, a neural tensor network is used to match the query set with the support set. In this way, InforMix-FKGC can learn few-shot relation embedding more precisely so as to enhance the accuracy of FKGC. Extensive experiments on the NELL-One and Wiki-One datasets demonstrate that InforMix-FKGC significantly outperforms ten state-of-the-art methods in terms of Mean Reciprocal Rank and Hits@K.