Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification
This work addresses a specific bottleneck in graph neural networks for researchers and practitioners in graph-based machine learning, offering an incremental improvement over existing methods.
The paper tackles the problem of semi-supervised node classification in graphs by addressing the conditional independence assumption in existing GNNs, proposing EPFGNN to model output-output relations explicitly, resulting in improved performance across various datasets.
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.