Geometric learning

So far, research on Deep Learning techniques has mainly focused on data defined on Euclidean domains (i.e., grids). However, in a multitude of different fields, such as Biology, Physics, Network Science, Recommender Systems and Computer Graphics, one may have to deal with data defined on non-Euclidean domains (i.e., graphs and manifolds). The adoption of Deep Learning in these fields has been lagging until very recently, primarily since the non-Euclidean nature of data makes the definition of basic operations (such as convolution) rather elusive.
Geometric Deep Learning deals with the extension of DL techniques to graph/manifold structured data. In this course, we will introduce this area of research by presenting recent research advancements in DL applied to point clouds, graphs, meshes and manifolds. Example applications will be illustrated in laboratory sessions.

Content
Convolutional Graph Neural Networks: Spatial and Spectral approaches
Graph Neural Networks message passing model
Attention in GNN
Graph pooling
Generalized convolutions: point cloud and meshes
Generative models and adversarial perturbations

PhD

6

Short Course

No registration fee.

June 11, 10.00-13.00 CEST and June 12, 10.00-13.00 CEST

English

Online, googleMeet

https://meet.google.com/kky-uqbe-vwm