arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1804.06188cs.LGcs.AIstat.ML
收藏

基于VC维的关系学习泛化界

VC-Dimension Based Generalization Bounds for Relational Learning

KU Leuven(鲁汶大学);ETH Zurich(苏黎世联邦理工学院);Cardiff University(卡迪夫大学)

Ondrej Kuzelka, Yuyi Wang, Steven Schockaert

摘要:

在关系学习的许多应用中,可用数据可以被视为来自更大关系结构的样本(例如,我们可能会从一些社交网络中获得一个小片段)。在本文中,我们特别关注的情况下,我们可以假设(i)出现在给定的样本中的域元素已被均匀采样,而没有从(未知的)完整域中替换,以及(ii)样本对于这些域元素是完整的(即,它是由这些元素引起的完整子结构)。在这种情况下,我们研究的误差界限充分统计的关系模型,估计可用的数据。作为我们的主要结果,我们证明了一个绑定的基础上的一个变种的Vapnik-Chervonenkis维,这是适合于关系数据。

英文摘要:

In many applications of relational learning, the available data can be seen as a sample from a larger relational structure (e.g. we may be given a small fragment from some social network). In this paper we are particularly concerned with scenarios in which we can assume that (i) the domain elements appearing in the given sample have been uniformly sampled without replacement from the (unknown) full domain and (ii) the sample is complete for these domain elements (i.e. it is the full substructure induced by these elements). Within this setting, we study bounds on the error of sufficient statistics of relational models that are estimated on the available data. As our main result, we prove a bound based on a variant of the Vapnik-Chervonenkis dimension which is suitable for relational data.

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。

↑