arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.00558cs.LGstat.ML
收藏

关系数据度量学习中的关系约束

Relational Constraints for Metric Learning on Relational Data

LS2N, UMR CNRS 6004(LS2N,法国国家科学研究中心联合研究单位6004);University of Nantes(南特大学)

Jiajun Pan, Hoel Le Capitaine, Philippe Leray

摘要:

大多数度量学习方法都致力于应用于由特征向量描述的数据,但也有一些值得注意的例外,如时间序列,树或图。本文的目的是提出一个度量学习算法,专门考虑关系数据。所提出的方法可以同时利用数据的拓扑结构和监督标签。为了选择表示关系信息的相对约束,我们引入了一个链接强度函数,该函数通过它们的共同父节点的边信息来度量实体之间的关系链接的强度。我们使用两种不同的经典学习算法,这是ITML(信息理论度量学习)和LSML(最小二乘度量学习)的性能,并在几个真实世界的数据集上进行测试。实验结果表明,使用关系信息提高了学习度量的质量。

英文摘要:

Most of metric learning approaches are dedicated to be applied on data described by feature vectors, with some notable exceptions such as times series, trees or graphs. The objective of this paper is to propose a metric learning algorithm that specifically considers relational data. The proposed approach can take benefit from both the topological structure of the data and supervised labels. For selecting relative constraints representing the relational information, we introduce a link-strength function that measures the strength of relationship links between entities by the side-information of their common parents. We show the performance of the proposed method with two different classical metric learning algorithms, which are ITML (Information Theoretic Metric Learning) and LSML (Least Squares Metric Learning), and test on several real-world datasets. Experimental results show that using relational information improves the quality of the learned metric.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑