Complete feature learning and consistent relation modeling for few-shot knowledge graph completion

Few-shot knowledge graph completion focuses on predicting unseen facts of long-tail relations in knowledge graphs with only few reference sets. The key challenge for tackling this task is how to represent the complete entity features under low data regime conditions and further build the relation scoring function of the triplet for prediction. However, existing works mainly focus on aggregating entity representations and seriously ignore the process of consistent relation modeling, resulting in unsatisfactory performance on sparse neighbors and complex relations modeling. To address the issues, this paper designs a two-branch feature extractor to capture complementary and complete representation of entities for differentiating the few examples, where each branch focuses on diverse aspect of the entity features. Furthermore, we apply a diversity loss based on the minimization of cosine similarity is applied between the two-branch feature extractors to encourage the two-branch to learn complementary features. Conditioned on the entity features, we further incorporate the structural relation representation into the semantic relation learning to keep the consistent with triplet scoring function, and consider the consistency issue of various structural relation modeling between training and test generalization. Empirical results on two public benchmark datasets NELL-One and Wiki-One demonstrate that our approach outperforms the state-of-the-art results, with relative improvements on Hits@10 for 1-shot of 4.8% and 4.4%, respectively, and achieves new state-of-the-art results. Additionally, Extensive experiments also show proficiency in dealing with complex relations and sparse neighbors. © 2023 Elsevier Ltd