Events

Upcoming events

2nd July 2025

Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms

Baran Hashemi, Kurt Pasque, Chris Teska, Ruriko Yoshida

preprint

No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets

Corinna Coupette, Jeremy Wayland, Emily Simons, Bastian Rieck

preprint

Past Events

28th May 2025

On Incorporating Scale into Graph Neural Networks

Christian Koke, Yuesong Shen, Abhishek Saroha, Marvin Eisenberger, Bastian Rieck, Michael Bronstein, Daniel Cremers

preprint recording

On the Expressive Power of Sparse Geometric MPNNs

Yonatan Sverdlov, Nadav Dym

preprint recording

26th March 2025

LLMs as GNNs (to understand how they generalize)

recording available on Youtube

Problems such as efficient (length) generalization are highly relevant for building agentic systems, yet they have puzzled LLM researchers for several years. However, they can sometimes be obvious through the lens of graph representation learning. This is because LLMs are, by their design, vulnerable to generalization issues from a variety of geometric perspectives.

A typical GNN researcher will already likely have a solid understanding of most of these perspectives! In this talk, we will use this knowledge, and attempt to scale the mountain of LLM generalization ⛰️

Petar Veličković

Research Scientist

Google Deepmind

19th February 2025

Discussion Session on the Future of Graph Learning Research

We want to use the February session to discuss what kind of research we want to do in graph learning in the next years and where we can make the most impact. Similar questions have already been discussed at length on big stages at various conferences. However, we think it is time to have this discussion with all graph learning enthusiasts, in particular (incoming) PhD students and postdocs who are actively shaping the field and whose research comprises the majority of what will be the field of graph learning in the next years. Whether you are excited, skeptical, curious, or frustrated about graph learning, we want to hear what you have to say!