CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Knowledge Graph Completion with Adaptive Sparse Transfer Matrix
Ji Guoliang; Liu Kang; He Shizhu; Zhao Jun
2016-02
会议名称AAAI Conference on Artificial Intelligence
会议日期2016年2月12日至17日
会议地点Phoenix, Arizona USA
摘要We model knowledge graphs for their completion by encoding each entity and relation into a numerical space. All previous work including Trans(E, H, R, and D) ignore the heterogeneity (some relations link many entity pairs and others do not) and the imbalance (the number of head entities and that of tail entities in a relation could be different) of knowledge graphs. In this paper, we propose a novel approach TranSparse to deal with the two issues. In TranSparse, transfer matrices are replaced by adaptive sparse matrices, whose sparse degrees are determined by the number of entities (or entity pairs) linked by relations. In experiments, we design structured and unstructured sparse patterns for transfer matrices and analyze their advantages and disadvantages. We evaluate our approach on triplet classification and link prediction tasks. Experimental results show that TranSparse outperforms Trans(E, H, R, and D) significantly, and achieves state-of-the-art performance.
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14516
专题模式识别国家重点实验室_自然语言处理
通讯作者Liu Kang
作者单位Institute of Automation, Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Ji Guoliang,Liu Kang,He Shizhu,et al. Knowledge Graph Completion with Adaptive Sparse Transfer Matrix[C],2016.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Knowledge Graph Comp(730KB)会议论文 开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Ji Guoliang]的文章
[Liu Kang]的文章
[He Shizhu]的文章
百度学术
百度学术中相似的文章
[Ji Guoliang]的文章
[Liu Kang]的文章
[He Shizhu]的文章
必应学术
必应学术中相似的文章
[Ji Guoliang]的文章
[Liu Kang]的文章
[He Shizhu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。