Title
Shaping GNNs with dynamical systems
Abstract
The dynamics of information diffusion in local message passing is a key issue that heavily influences graph representation learning, especially when long-range propagation is needed. We vouch for principled approaches that control and regulate the degree of propagation, conservation and dissipation of information throughout the neural flow. In the talk we explore some approaches stemming from a dynamical systems' view of neural networks for static and temporal graphs, with particular focus on wide applicability of the concepts and on the theoretical guarantees on information conservation.
Bio
Davide Baccius is a Professor in Machine Learning, at the Computer Science Department, University of Pisa, where he is also the head of the Pervasive Artificial Intelligence Laboratory (PAILab). Link to Bacciu's professional website.
Speaker is presenting online.
Practical
The Tuesdays seminars series are devoted to various topics relevant for the Integreat´s research focus. Presenters from the Integreat community and beyond have 40 minutes to present, followed by a group discussion.
Seminars are open for attendance for everybody.
For those unable to attend in person: https://uio.zoom.us/j/62535744013
Point of contacts:
- Organiser and moderator: Veronica Lachi, UiT
- Integreat Administrative Leader Maria Dikova, UiO