Higher-order Sparse Convolutions in Graph Neural Networks

Autor:	Giraldo, Jhony H., Javed, Sajid, Mahmood, Arif, Malliaros, Fragkiskos D., Bouwmans, Thierry
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Electrical Engineering and Systems Science - Signal Processing
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted in IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2302.10505 Zobrazit plný text záznamu View this record from Arxiv