Node features and structural information of a graph are both crucial for semi-supervised node classification problems. A variety of graph neural network (GNN) based approaches have been proposed to tackle these problems, which typically determine output labels through feature aggregation. This can be problematic, as it implies conditional independence of output nodes given hidden representations, despite their direct connections in the graph. To learn the direct influence among output nodes in a graph, we propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field. It contains explicit pairwise factors to model output-output relations and uses a GNN backbone to model input-output relations. To balance model complexity and expressivity, the pairwise factors have a shared component and a separate scaling coefficient for each edge. We apply the EM algorithm to train our model, and utilize a star-shaped piecewise likelihood for the tractable surrogate objective. We conduct experiments on various datasets, which shows that our model can effectively improve the performance for semi-supervised node classification on graphs.
翻译:图形的节点特征和结构信息对于半监督节点分类问题都至关重要。 已经提出了各种基于图形神经网络(GNN)的方法来解决这些问题, 通常通过特性聚合来决定输出标签。 这可能是个问题, 因为它意味着输出节点具有有条件的独立性, 尽管在图形中有直接连接。 要在图形中了解输出节点之间的直接影响, 我们建议使用“ 透明、 透明、 因素化的图像神经网络 ” ( EPFGNN), 将整个图形作为部分观测到的Markov 随机字段。 它含有模拟输出输出- 输出关系的明确的对等因素, 并使用 GNN 主干柱来模拟输入- 输出关系 。 为了平衡模型的复杂性和表达性, 配对因素有一个共同的组件, 以及每个边缘的单独缩放系数 。 我们应用 EM 算法来训练我们的模型, 并使用恒星形的奇形可能性来达到可引力的代号目标 。 我们在各种数据集上进行实验, 这表明我们的模型可以有效地改进图形中半超节点分类的性。