Efficient Weight Learning in High-Dimensional Untied MLNs
Efficient Weight Learning in High-Dimensional Untied MLNs
复制标题
高维无约束 MLN 中的高效权重学习
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
D. Venugopal
中科院分区：
文献类型：
--
作者：
Khan Mohammad Al Farabi;Somdeb Sarkhel;D. Venugopal
当 MLN 的参数绑定时，即 MLN 中的多个基本公式共享相同的权重时，用于提高马尔可夫逻辑网络 (MLN) 中权重学习的可扩展性的现有技术通常是有效的。然而，为了提高现实世界问题的准确性，我们通常需要为 MLN 的不同基础学习单独的权重。在本文中，我们提出了一种在包含高维、无束缚公式的 MLN 中执行有效权重学习的方法。我们方法的基本思想是通过以下方式帮助学习算法更有效地导航参数搜索空间：a）将可能具有相似权重的未绑定公式的基础捆绑在一起，b）为参数设置良好的初始值。为此，我们遵循分层方法，首先使用非关系学习器学习要绑定的参数。然后，我们使用关系学习器来学习绑定参数 MLN，其初始值源自非关系学习器学习的参数。我们阐述了我们的方法对三个不同的现实问题的前景，并表明与现有最先进的关系学习系统相比，我们的方法产生了更具可扩展性和更准确的结果。
Existing techniques for improving scalability of weight learning in Markov Logic Networks (MLNs) are typically effective when the parameters of the MLN are tied, i.e., several ground formulas in the MLN share the same weight. However, to improve accuracy in realworld problems, we typically need to learn separate weights for different groundings of the MLN. In this paper, we present an approach to perform efficient weight learning in MLNs containing high-dimensional, untied formulas. The fundamental idea in our approach is to help the learning algorithm navigate the parameter search-space more efficiently by a) tying together groundings of untied formulas that are likely to have similar weights, and b) setting good initial values for the parameters. To do this, we follow a hierarchical approach, where we first learn the parameters that are to be tied using a non-relational learner. We then use a relational learner to learn the tiedparameter MLN with initial values derived from parameters learned by the non-relational learner. We illustrate the promise of our approach on three different real-world problems and show that our approach yields much more scalable and accurate results compared to existing state-of-the-art relational learning systems.
无限制 MLN 的高效推理
DOI：
10.24963/ijcai.2017/644
发表时间：
2017
期刊：
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
影响因子：
--
作者：
Sarkhel, Somdeb;Venugopal, Deepak;Ruozzi, Nicholas;Gogate, Vibhav
通讯作者：
Gogate, Vibhav