Sum-Product Networks (SPNs) are expressive probabilistic models that provide exact, tractable inference. They achieve this efficiency by making used of local independence. On the other hand, mixtures of exchangeable variable models (MEVMs) are a class of tractable probabilistic models that make use of exchangeability of random variables to render inference tractable. Exchangeability, which arises naturally in systems consisting of multiple, interrelated entities, has not been considered for efficient representation and inference in SPNs yet. The contribution of this paper is a novel probabilistic model which we call Exchangeability-Aware Sum-Product Networks (XSPNs). It contains both SPNs and MEVMs as special cases, and combines the ability of SPNs to efficiently learn deep probabilistic models with the ability of MEVMs to efficiently handle exchangeable random variables. We also introduce a structure learning algorithm for XSPNs and empirically show that they can be more accurate and efficient than conventional SPNs when the data contains repeated, interchangeable parts.
翻译:平价生产网络(SPNs)是提供精确、可移动推论的直观概率模型,它们通过利用当地独立实现这一效率。另一方面,可交换可变模型(MEVMs)的混合物是一种可移动概率模型,利用随机变量的互换性使推论可移动。在由多个相互关联的实体组成的系统中自然产生的可交换性尚未被考虑用于在SPNs中进行有效的表述和推断。本文的贡献是一个新型的概率模型,我们称之为“可交换性-软件总和生产网络(XSPns) ” 。它包含SPNs和MEVMs作为特例,并将SPNs有效学习深度概率模型的能力与MEVMs有效处理可交换随机变量的能力结合起来。我们还引入了XSPNs的结构学习算法,并有经验地表明,当数据包含重复、可交换部分时,它们比常规的SPNs更准确、更有效率。