Knowledge Commons of Institute of Automation,CAS
A Re-Ranking Framework for Knowledge Graph Completion | |
Wang, Zikang1; Li, Linjing1,2,3; Zeng, Daniel1,2,3 | |
2020-07 | |
会议名称 | The 2020 International Joint Conference on Neural Networks (IJCNN) |
会议日期 | 2020.7.19-24 |
会议地点 | Glasgow, Scotland, UK |
出版者 | IEEE |
摘要 | 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. |
关键词 | knowledge graph, link prediction, attention mechanism |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 知识表示与推理 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40640 |
专题 | 多模态人工智能系统全国重点实验室_互联网大数据与信息安全 |
通讯作者 | Li, Linjing |
作者单位 | 1.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 3.Shenzhen Artificial Intelligence and Data Science Institute (Longhua), Shenzhen, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wang, Zikang,Li, Linjing,Zeng, Daniel. A Re-Ranking Framework for Knowledge Graph Completion[C]:IEEE,2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Zikang_2020.pdf(447KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论