Private and Shared Feature Extractors Based on Hierarchical Neighbor Encoder for Adaptive Few-Shot Knowledge Graph Completion

While Knowledge Graphs (KGs) have been applied in many AI tasks, KGs are known for being incomplete with many missing facts. Previous works rely on a large number of training data for KG completion. However, there are often few entity pairs available for most relations in KGs. In this paper, we propose a Few-shot Knowledge Graph Completion (FKGC) model, named Private and Shared feature extractors based on Hierarchical neighbor encoder for Adaptive few-shot knowledge graph completion (PSHA). In the PSHA model, we first exploit the hierarchical attention mechanism to extract the inherent and valuable hidden information of the neighborhood surrounding the entity. Following that, we adopt a private feature extractor to extract the private features of relation information of the entity pairs, and then a shared feature extractor is used to extract the shared features of the entity pairs of the support set. In addition, an adaptive aggregator aggregates entity pairs of the support set about the query. We conduct experiments on the 2-shot and 5-shot of the NELL-One and CoDEx-S-One dataset. The experimental results show that the PSHA outperforms the existing FKGC models in both scenarios.