Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
复制标题
DOI：
10.1145/3308558.3313612
复制
发表时间：
2019-03
期刊：
影响因子：
--
通讯作者：
Wen Zhang;B. Paudel;Liang Wang;Jiaoyan Chen;Hai Zhu;Wei Zhang-;A. Bernstein;Huajun Chen
中科院分区：
文献类型：
--
作者：
Wen Zhang;B. Paudel;Liang Wang;Jiaoyan Chen;Hai Zhu;Wei Zhang-;A. Bernstein;Huajun Chen
推理对于大型知识图的开发至关重要，特别是对于完成，其目的是基于现有的三元组推断新的三元组。规则和嵌入都可以用于知识图推理，它们有各自的优点和困难。基于规则的推理是准确的和可解释的，但规则学习与搜索的图总是受到效率，由于巨大的搜索空间。基于嵌入的推理更具有可扩展性和效率，因为推理是通过嵌入之间的计算进行的，但它很难学习稀疏实体的良好表示，因为良好的嵌入在很大程度上依赖于数据丰富性。基于这种观察，在本文中，我们将探讨如何将嵌入和规则学习结合在一起，并利用各自的优势互补彼此的困难。我们提出了一个新的框架IterE迭代学习嵌入和规则，其中规则是从嵌入学习适当的修剪策略和嵌入学习现有的三元组和新的三元组的规则推断。对IterE嵌入质量的评估表明，规则有助于提高稀疏实体嵌入的质量和链接预测结果。我们还评估了规则学习的效率和质量的规则从IterE相比，AMIE+，表明IterE是能够更有效地生成高质量的规则。实验表明，迭代学习嵌入和规则在学习和预测过程中相互受益。
Reasoning is essential for the development of large knowledge graphs, especially for completion, which aims to infer new triples based on existing ones. Both rules and embeddings can be used for knowledge graph reasoning and they have their own advantages and difficulties. Rule-based reasoning is accurate and explainable but rule learning with searching over the graph always suffers from efficiency due to huge search space. Embedding-based reasoning is more scalable and efficient as the reasoning is conducted via computation between embeddings, but it has difficulty learning good representations for sparse entities because a good embedding relies heavily on data richness. Based on this observation, in this paper we explore how embedding and rule learning can be combined together and complement each other's difficulties with their advantages. We propose a novel framework IterE iteratively learning embeddings and rules, in which rules are learned from embeddings with proper pruning strategy and embeddings are learned from existing triples and new triples inferred by rules. Evaluations on embedding qualities of IterE show that rules help improve the quality of sparse entity embeddings and their link prediction results. We also evaluate the efficiency of rule learning and quality of rules from IterE compared with AMIE+, showing that IterE is capable of generating high quality rules more efficiently. Experiments show that iteratively learning embeddings and rules benefit each other during learning and prediction.