Skip to main content

Register HERE

Graph Neural Networks (GNNs) have marked a groundbreaking shift in machine learning on graphs by enabling the flexible integration of both node and edge information, while harnessing the expressiveness of the neural network machinery. This innovation has led to a wide spectrum of applications across the physical and biological sciences, ranging from cosmology, spatial transcriptomics, or drug discovery.

Over the course of two days, this workshop will offer participants a platform to explore recent developments in Graph Neural Network (GNN) methodologies and to discuss both the challenges and successes encountered in applying GNNs to real-world data. The workshop will feature a mix of plenary talks, flash talks, and poster sessions, with the aim of fostering exchanges on GNNs’ role in advancing scientific research.

We strongly encourage participants to actively contribute to the workshop by presenting their work, either through a 30-minute oral presentation or during the poster sessions.
Topics of interest to this workshop include (but are not restricted to): new GNN methods, theoretical results on GNN, and applications of GNN to physics and biology. You can register for a presentation on the registration page.

Full event schedule available HERE

Questions? Contact Claire Donnat:


Lorenzo Orecchia

Assistant Professor, Computer Science

Andrew Ferguson

Associate Professor of Molecular Engineering

Claire Donnat

Assistant Professor, Department of Statistics

Risi Kondor

Associate Professor, Department of Computer Science, Department of Statistics, Computational and Applied Mathematics Initiative (CAMI)