ParamE: Regarding Neural Network Parameters as Relation Embeddings for Knowledge Graph Completion | |
Feihu Che2,3; Dawei Zhang3; Jianhua Tao1,2,3; Mingyue Niu2,3; Bocheng Zhao2,3 | |
2020-04-03 | |
会议日期 | 2020-2-7 |
会议地点 | 美国纽约 |
英文摘要 | We study the task of learning entity and relation embeddings in knowledge graphs for predicting missing links. Previous translational models on link prediction make use of translational properties but lack enough expressiveness, while the convolution neural network based model (ConvE) takes advantage of the great nonlinearity fitting ability of neural networks but overlooks translational properties. In this paper, we propose a new knowledge graph embedding model called ParamE which can utilize the two advantages together. In ParamE, head entity embeddings, relation embeddings and tail entity embeddings are regarded as the input, parameters and output of a neural network respectively. Since parameters in networks are effective in converting input to output, taking neural network parameters as relation embeddings makes ParamE much more expressive and translational. In addition, the entity and relation embeddings in ParamE are from feature space and parameter space respectively, which is in line with the essence that entities and relations are supposed to be mapped into two different spaces. We evaluate the performances of ParamE on standard FB15k-237 and WN18RR datasets, and experiments show ParamE can significantly outperform existing state-of-the-art models, such as ConvE, SACN, RotatE and D4-STE/Gumbel. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48831] ![]() |
专题 | 模式识别国家重点实验室_智能交互 |
通讯作者 | Jianhua Tao |
作者单位 | 1.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 3.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China |
推荐引用方式 GB/T 7714 | Feihu Che,Dawei Zhang,Jianhua Tao,et al. ParamE: Regarding Neural Network Parameters as Relation Embeddings for Knowledge Graph Completion[C]. 见:. 美国纽约. 2020-2-7. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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