.png){kind=icon}
返回
Knowledge Graph Completion by Jointly Learning Structural Features and Soft Logical Rules
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2021.3108224.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With the rapid development and widespread application of Knowledge graphs (KGs) in many artificial intelligence tasks, a large number of efforts have been made to refine them and increase their quality. Knowedge graph embedding (KGE) has become one of the main refinement tasks, which aims to predict missing facts based on existing ones in KGs. However, there are still mainly two difficult unresolved challenges: (i) how to leverage the local structural features of entities and the potential soft logical rules to learn more expressive embedding of entites and relations; and (ii) how to combine these two learning processes into one unified model. To conquer these problems, we propose a novel KGE model named JSSKGE, which can Jointly learn the local Structural features of entities and Soft logical rules. First, we employ graph attention networks which are specially designed for graph-structured data to aggregate the local structural information of nodes. Then, we utilize soft logical rules implicated in KGs as an expert to further rectify the embeddings of entities and relations. By jointly learning, we can obtain more informative embeddings to predict new facts. With experiments on four commonly used datasets, the JSSKGE obtains better performance than state-of-the-art approaches.
Keyword:
Task analysis
Predictive models
Training
Knowledge engineering
Deep learning
Neural networks
Convolutional neural networks
Knowledge graph completion
knowledge graph embedding
graph attention neural networks
link prediction
soft logical rules
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W
机构
引用论文
Kinematic analysis of limb movements in neuropsychological research: Subtle deficits and recovery of function.神经心理学研究中肢体运动的运动学分析: 细微的缺陷和功能的恢复。
PREAI
分享收藏DBpedia - A large-scale, multilingual knowledge base extracted from WikipediaDBpedia-从维基百科中提取的大规模多语言知识库.png)
SEMANTIC WEB
OAAI
SEMANTIC WEBIF2.9
OAAI分享收藏Monoclonal Antibodies to Meningococcal Factor H Binding Protein with Overlapping Epitopes and Discordant Functional ActivityPLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏Blunt popliteal artery injury following tibiofemoral trauma: vessel-first and bone-first strategyOAAI
OAAI分享收藏
查看更多内容