GraphHop++: New Insights into GraphHop and Its Enhancement

An enhanced label propagation (LP) method called GraphHop has been proposed recently. It outperforms graph convolutional networks (GCNs) in the semi-supervised node classification task on various networks. Although the performance of GraphHop was explained intuitively with joint node attributes and labels smoothening, its rigorous mathematical treatment is lacking. In this paper, new insights into GraphHop are provided by analyzing it from a constrained optimization viewpoint. We show that GraphHop offers an alternate optimization to a certain regularization problem defined on graphs. Based on this interpretation, we propose two ideas to improve GraphHop furthermore, which leads to GraphHop++. We conduct extensive experiments to demonstrate the effectiveness and efficiency of GraphHop++. It is observed that GraphHop++ outperforms all other benchmarking methods, including GraphHop, consistently on five test datasets as well as an object recognition task at extremely low label rates (i.e., 1, 2, 4, 8, 16, and 20 labeled samples per class).