Structure-augmented knowledge graph embedding for sparse data with rule learning
Structure-augmented knowledge graph embedding for sparse data with rule learning
复制标题
通过规则学习稀疏数据的结构增强知识图嵌入
DOI：
10.1016/j.comcom.2020.05.017
复制
发表时间：
2020-06
影响因子：
6
通讯作者：
Jin Hai
中科院分区：
文献类型：
--
作者：
Zhao Feng;Sun Haoran;Jin Langjunqing;Jin Hai
近年来，知识图由于其表达丰富信息的能力以及在基于知识的推理中的应用潜力而受到了相当大的关注。例如，它们可以协助与用户关联、切换策略和移动的服务中的流量内容相关的深入知识发现。知识图嵌入将知识图的实体和关系投影到密集且低维的向量中，从而允许有效地测量这些实体之间的复杂语义信息和关系。然而，传统的知识图嵌入方法只考虑直接事实，在面对稀疏数据时难以实现实体和关系的合理嵌入学习。针对这一问题，提出了一种基于张量分解和规则学习的知识图嵌入方法。首先，根据实体和关系的初始嵌入来推断规则并进行评分。然后，新的三元组稀疏实体推断出高分数的规则。最后，这些新的三元组被迭代地嵌入到模型中。在WN18和FB15k数据集上的实验结果表明，该模型在面对稀疏数据时的性能明显优于其他最先进的知识图嵌入模型.
In recent years, knowledge graphs have received considerable attention because of their ability to express rich information and their potential for use in knowledge-based reasoning. For example, they can assist in-depth knowledge discovery related to user associations, switching policies, and traffic content in mobile services. Knowledge graph embeddings project the entities and relations of knowledge graphs into vectors that are dense and low dimensional, thus allowing the complex semantic information and relations between these entities to be measured efficiently. However, traditional knowledge graph embedding methods consider only direct facts, making it difficult to achieve reasonable embedding learning of entities and relations when faced with sparse data. To settle this issue, this paper proposes a novel knowledge graph embedding method based on tensor decomposition combined with rule learning. First, rules are inferred and scored based on the initial embeddings of entities and relations. Then, new triples for sparse entities are inferred from rules with high scores. Finally, these new triples are iteratively embedded into the model. Experimental results obtained on theWN18andFB15kdatasets indicate that the proposed model achieves significantly better performance than other state-of-the-art knowledge graph embedding models when faced with sparse data.
登录
查看更多内容
DOI：
10.18653/v1/d17-1060
发表时间：
2017-07
期刊：
--
影响因子：
--
作者：
Wenhan Xiong;Thi-Lan-Giao Hoang;William Yang Wang
通讯作者：
Wenhan Xiong;Thi-Lan-Giao Hoang;William Yang Wang
DOI：
10.1145/3308558.3313612
发表时间：
2019-03
期刊：
The World Wide Web Conference
影响因子：
--
作者：
Wen Zhang;B. Paudel;Liang Wang;Jiaoyan Chen;Hai Zhu;Wei Zhang-;A. Bernstein;Huajun Chen
通讯作者：
Wen Zhang;B. Paudel;Liang Wang;Jiaoyan Chen;Hai Zhu;Wei Zhang-;A. Bernstein;Huajun Chen
知识图中的混合推理：符号推理和统计推理的结合
DOI：
10.3233/sw-190375
发表时间：
2020-01
期刊：
Semantic Web Journal
影响因子：
--
作者：
Weizhuo Li;Guilin Qi;Qiu Ji
通讯作者：
Qiu Ji
DOI：
10.3115/v1/p15-1067
发表时间：
2015-07
期刊：
--
影响因子：
--
作者：
Guoliang Ji;Shizhu He;Liheng Xu;Kang Liu;Jun Zhao
通讯作者：
Guoliang Ji;Shizhu He;Liheng Xu;Kang Liu;Jun Zhao
DOI：
10.1007/978-3-319-42911-3_3
发表时间：
2016-08
期刊：
--
影响因子：
--
作者：
Molood Barati;Q. Bai;Qing Liu
通讯作者：
Molood Barati;Q. Bai;Qing Liu