Abstract

Join us on Zoom

Deep learning has successfully transformed how we tackle different problems, especially in the fields of image/text recognition and generation. However, most methods remained constrained to these grid-like data structures and struggle to translate to more complex geometries such as meshes and graphs. Having powerful deep learning on graphs will unlock an unprecedented number of applications in different fields, such as social networks, road navigation, and drug discovery. In this talk, I will discuss the main challenges of applying deep learning on graphs, why early methods have struggled, and how spectral theory is one of the main keys in unlocking graph deep learning. Specifically, I will discuss some of our recent work including “Directional Graph Networks”, which offers the first generalization of convolutional neural networks to graphs, and “Rethinking Graph Transformers with Spectral Attention”, which offers the first generalization of Transformers to graphs.

BIO:

Dominique is the Head of Graph Research at “Valence Discovery”, a startup located at the Montreal Institute of Learning Algorithms (MILA). Our mission focuses on unlocking deep learning for drug discovery via property prediction, screening, and generation. We currently collaborate with multiple pharmaceutical companies and research laboratories to help them find better drugs, faster, cheaper, and with fewer side effects.