Open Knowledge Graph Representation Learning Based on Neighbors and Semantic Affinity
-
摘要: 知识图谱(knowledge graph， KG)打破了不同场景下的数据隔离，为实际应用提供基础支持.表示学习将KG转换到低维向量空间来为KG应用提供便利.然而，KG的表示学习目前存在2个问题：1)假设KG满足闭合世界假设，要求所有实体在训练中可见.实际上，大多数KG都在快速增长，例如DBPedia平均每天产生200个新实体.2)采用矩阵映射、卷积等复杂的语义交互方式提高模型的准确性，这样做也限制了模型的可扩展性.为此，针对允许新实体存在的开放KG，提出一种表示学习方法TransNS.它选取相关的邻居作为实体的属性来推断新实体，并在学习阶段利用实体之间的语义亲和力选择负例三元组来增强语义交互能力.5个传统数据集和8个新数据集对比了TransNS与最经典的表示学习方法，结果表明：TransNS在开放KG上表现良好，甚至在基准闭合KG上优于现有模型.Abstract: Knowledge graph (KG) breaks the data isolation in different scenarios and provides basic support for the practical application. The representation learning transforms KG into the low-dimensional vector space to facilitate KG application. However, there are two problems in KG representation learning: 1)It is assumed that KG satisfies the closed-world assumption. It requires all entities to be visible during the training. In reality, most KGs are growing rapidly, e.g. a rate of 200 new entities per day in the DBPedia. 2)Complex semantic interaction, such as matrix projection and convolution, are used to improve the accuracy of the model and limit the scalability of the model. To this end, we propose a representation learning method TransNS for open KG that allows new entities to exist. It selects the related neighbors as the attribute of the entity to infer the new entity, and uses the semantic affinity between the entities to select the negative triple in the learning phase to enhance the semantic interaction capability. We compare our TransNS with the state-of-the-art baselines on 5 traditional and 8 new datasets. The results show that our TransNS performs well in the open KGs and even outperforms existing models on the baseline closed KGs.
-
Keywords:
- knowledge graph /
- representation learning /
- open-world assumption /
- neighbors /
- semantic affinity
-
-
期刊类型引用(7)
1. 姜磊，章小卫. 基于模糊隶属度邻域覆盖的三支分类决策. 计算机应用与软件. 2024(02): 271-278 . 
百度学术
2. 骆公志，张尚蕾. 基于正区域和投票式属性重要度的特征提取算法. 南京邮电大学学报(自然科学版). 2024(01): 79-89 . 百度学术
3. 王笑笑，巴婧，陈建军，宋晶晶，杨习贝. 超约简求解：效率与性能的提升. 计算机科学. 2023(02): 166-172 . 百度学术
4. 刘长顺，刘炎，宋晶晶，徐泰华. 基于论域离散度的属性约简算法. 山东大学学报(理学版). 2023(05): 26-35+52 . 百度学术
5. 张清华，艾志华，张金镇. 融合密度与邻域覆盖约简的分类方法. 陕西师范大学学报(自然科学版). 2022(03): 33-42 . 百度学术
6. 沈毅波. RBF神经网络在关联数据一致性挖掘中的应用. 福建电脑. 2022(08): 5-9 . 百度学术
7. 周长顺，徐久成，瞿康林，申凯丽，章磊. 一种基于改进邻域粗糙集中属性重要度的快速属性约简方法. 西北大学学报(自然科学版). 2022(05): 745-752 . 百度学术
其他类型引用(7)
计量
- 文章访问数: 1330
- HTML全文浏览量: 4
- PDF下载量: 752
- 被引次数: 14
下载:
