Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification

Abstract

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.

arXiv commentAccepted for publication in AAAI 2024

References in corpus (6)

• Predict then Propagate: Graph Neural Networks meet Personalized PageRank
• A Gentle Introduction to Deep Learning for Graphs
• Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
• Wasserstein Weisfeiler-Lehman Graph Kernels
• Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited
• Convolutional Kernel Networks for Graph-Structured Data