A Re-Ranking Framework for Knowledge Graph Completion

Zikang Wang, Linjing Li, Daniel Dajun Zeng

Abstract

Knowledge graph completion, one of the most important research questions in knowledge graphs, aims at predicting missing links in a given graph. Current mainstream approaches adopt high-quality embeddings of entities and relations of the graph to improve their performances. However, it is not easy to devise a universal embedding learner that can fit various scenarios. In this paper, we propose a general-purpose framework which can be employed to improve the performance of knowledge graph completion. Specifically, given an arbitrary knowledge graph completion model, we first run the original model to get a ranked entity list. Then, we combine the query and the top ranked entities with attention mechanism, re-rank all these entities by feeding the combined vector into a neural network. The proposed re-ranking phase can be conveniently added to a variety of models to improve their performance without substantial modification. We conduct experiments on four datasets: WN18, FB15k, WN18RR, and FB15k-237. We choose TransE, TransH, TransD, DistMult, and ANALOGY as base models. Experiments on these datasets and models validate the effectiveness of the proposed re-ranking framework. We further explore the influence of the number of top ranked entities used in the re-ranking phase. We also test other attention mechanism to determine the most effective one, and found that vanilla attention mechanism can balance accuracy and complexity.
BibTeX
@inproceedings{wang2020re,
  author = {Zikang Wang and Linjing Li and Daniel Dajun Zeng},
  title = {{A Re-Ranking Framework for Knowledge Graph Completion}},
  booktitle = {IJCNN},
  year = {2020},
  doi = {10.1109/ijcnn48605.2020.9207439},
}

Loading related content...

Figure