Graphs are a powerful data structure to represent relational data and are widely used to describe complex real-world data structures. Probabilistic Graphical Models (PGMs) have been well-developed in the past years to mathematically model real-world scenarios in compact graphical representations of distributions of variables. Graph Neural Networks (GNNs) are new inference methods developed in recent years and are attracting growing attention due to their effectiveness and flexibility in solving inference and learning problems over graph-structured data. These two powerful approaches have different advantages in capturing relations from observations and how they conduct message passing, and they can benefit each other in various tasks. In this survey, we broadly study the intersection of GNNs and PGMs. Specifically, we first discuss how GNNs can benefit from learning structured representations in PGMs, generate explainable predictions by PGMs, and how PGMs can infer object relationships. Then we discuss how GNNs are implemented in PGMs for more efficient inference and structure learning. In the end, we summarize the benchmark datasets used in recent studies and discuss promising future directions.
翻译:图表是代表关联数据的强大数据结构,广泛用于描述复杂的真实世界数据结构。过去几年来,概率图形模型(PGMs)已经发展得相当完善,在变量分布的缩略图中以数学方式模拟真实世界情景。图表神经网络(GNNs)是近年来开发的新的推论方法,由于在解决图表结构数据中的推论和学习问题方面的有效性和灵活性,正在引起越来越多的注意。这两种强有力的方法在捕捉观测和如何传递信息的关系以及它们如何在各种任务中相互受益方面有着不同优势。在本调查中,我们广泛研究GNs和PGMs之间的交叉点。具体地说,我们首先讨论GNNs如何从在 PGMs 中学习结构化的表述中得益,产生PGMs可解释的预测,以及PGMs如何推断对象关系。然后我们讨论在PGMs中如何执行GNs,以提高效率的推论和结构学。我们最后总结了最近研究中所使用的基准数据集,并讨论有希望的未来方向。