Graph neural networks are a neural network architecture specifically designated to handle graph-type data. Different from traditional neural networks, GNNs, fall under the larger umbrella of Geometric Deep Learning which focuses on leveraging geometric information about the data to improve the network's predictions.
Papers
PRESENTATIONS
The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited
Floriano Tori, Vincent Holst, & Vincent Ginis
Presented at the 3rd Learning on Graph Conference, 2024