Attention-based Multi-hop Reasoning for Knowledge Graph | |
Wang Zikang1,2; Li Linjing1; Zeng Daniel1,2; Chen Yue3 | |
2018-11 | |
会议名称 | IEEE International Conference on Intelligence and Security Informatics |
会议日期 | 2018.11.08-10 |
会议地点 | 美国,迈阿密 |
摘要 | Knowledge graph plays an important role in de- tection, prediction, early warning, and other security related applications. A fundamental task in applying knowledge graph is the so-called multi-hop reasoning, which focuses on inferring new relations between entities. In this paper, we introduce attention mechanism to the classic compositional method. After finding reasoning paths between entities, we aggregate these paths’ embeddings into one according to their attentions, and infer the relation of entities based on the combined embedding. Two experiments on NELL-995 dataset, fact prediction and link prediction, validated that our method outperforms all baselines. |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44374 |
专题 | 复杂系统管理与控制国家重点实验室_互联网大数据与信息安全 |
作者单位 | 1.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.CNCERT/CC 3.chool of Computer and Control Engineering, University of Chinese Academy of Sciences |
第一作者单位 | 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,et al. Attention-based Multi-hop Reasoning for Knowledge Graph[C],2018. |
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 | ||
2018_isi_multi-hop_a(618KB) | 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