Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification

We present a deep Graph Convolutional Kernel Machine (GCKM) for semi-supervised node classification in graphs. The method is built of two main types of blocks: (i) We introduce unsupervised kernel machine layers propagating the node features in a one-hop neighborhood, using implicit node feature mappings. (ii) We specify a semi-supervised classification kernel machine through the lens of the Fenchel-Young inequality. We derive an effective initialization scheme and efficient end-to-end training algorithm in the dual variables for the full architecture. The main idea underlying GCKM is that, because of the unsupervised core, the final model can achieve higher performance in semi-supervised node classification when few labels are available for training. Experimental results demonstrate the effectiveness of the proposed framework. Contributions We introduce a deep Graph Convolutional Kernel Machine (GCKM) for node classification made of multiple shallow layers with non-parametric aggregation functions. Our main contributions are the following. • We propose an architecture consisting of multiple unsu-