IEEE

Beyond Message-Passing: Generalization of Graph Neural Networks via Feature Perturbation for Semi-Supervised Node Classification

Abstract: Graph neural networks (GNNs) that collect information from neighbors are commonly utilized in semi-supervised learning contexts. In particular, a significant body of research has been ...
GitHub

Tutorial on seismic signal/noise classification; from linear to deep classifiers

This jupyter notebook tutorial is meant to be a general introduction to machine and deep learning. We use seismic time series data from i) real earthquakes and ii) nuisance signals to train a suite of ...
IEEE

Automatic Design of Deep Graph Neural Networks With Decoupled Mode

Abstract: Graph neural networks (GNNs), a class of deep learning models designed for performing information interaction on non-Euclidean graph data, have been successfully applied to node ...