Geometric deep learning, a novel class of machine learning algorithms extending classical deep learning architectures to non-Euclidean structured data such as manifolds and graphs, has recently been applied to a broad spectrum of problems ranging from computer graphics and chemistry to high energy physics and social media. In this paper, we propose SIGN, a scalable graph neural network analogous to the popular inception module used in classical convolutional architectures. We show that our architecture is able to effectively deal with large-scale graphs via pre-computed multi-scale neighborhood features. Extensive experimental evaluation on various open benchmarks shows the competitive performance of our approach compared to a variety of popular architectures, while requiring a fraction of training and inference time.
Speakers: Fabrizio Frasca, Emanuele Rossi, Davide Eynard, Benjamin Chamberlain, Michael Bronstein, Federico Monti