Higher-order Sparse Convolutions in Graph Neural Networks
Jhony H. Giraldo (Télécom Paris); Sajid Javed (Khalifa University of Science and Technology); Arif Mahmood (Information Technology University); Fragkiskos Malliaros (CentraleSupelec); Thierry BOUWMANS (Univ. La Rochelle)
-
SPS
IEEE Members: $11.00
Non-members: $15.00
Graph Neural Networks (GNNs) have been applied to many problems in computer sciences. Capturing higher-order relationships between nodes is crucial to increase the expressive power of GNNs. However, existing methods to capture these relationships could be infeasible for large-scale graphs. In this work, we introduce a new higher-order sparse convolution based on the Sobolev norm of graph signals. Our Sparse Sobolev GNN (S-SobGNN) computes a cascade of filters on each layer with increasing Hadamard powers to get a more diverse set of functions, and then a linear combination layer weights the embeddings of each filter. We evaluate S-SobGNN in several applications of semi-supervised learning. S-SobGNN shows competitive performance in all applications as compared to several state-of-the-art methods.