In this paper, we propose a graph neural network that employs high-pass filters in the convolutional layers. To do this, we depart from a linear model for the convolutional layer and consider the case of directed graphs. This allows for graph spectral theory and the connections between eigenfunctions over the graph and Fourier analysis to employ graph signal processing to obtain an architecture that “concatenates” low and high-pass filters to process data on a connected graph. This yields a method that is quite general in nature applicable to directed and undirected graphs and with clear links to graph spectral methods, Fourier analysis and graph signal processing. Here, we illustrate the utility of our graph convolutional approach to the classification using citation datasets and knowledge graphs. The results show that our method provides a margin of improvement over the alternative.
Torsello A, Rossi L, Pelillo M, Biggio B, Robles-Kelly A
Title of proceedings
S+SSPR 2021 : Proceedings of the IAPR International Workshops on Structural, Syntactic, and Statistical Pattern Recognition and Statistical Techniques in Pattern Recognition
Event
International Association of Pattern Recognition. Workshops (2021 : Online from Italy)
Publisher
Springer
Place of publication
Cham, Switzerland
Series
International Association of Pattern Recognition Workshops