Martin Carrasco

I am ELLIS Doctoral Student @ AIDOS supervised by Prof. Bastian Rieck and co-supervised by Prof. Søren Hauberg.

My research focuses on geometrical and topological methods in machine learning. In a nutshell, I really like graphs and shapes. Also seems like they can be useful in AI.

Past work

On efficient TDL

I started my journey in applications of topological deep learning when working with Dr. Telyatnikov and Dr. Bernardez from REAL AI. We have a preprint out on efficient ways to perform higher-order message passing. Check it out here .

On graph metrics

For my M.Sc. thesis I was supervised by Prof. Erik Bekkers from AMLab and Prof. Bastian Rieck. I explored an alternative metric that fully characterizes attributed graphs (in expectation), it’s relationship to homomorphism counts and how it can be used as an inductive bias in message passing neural netowrks (MPNN). We put out a preprint with some of our findings here

My current interests (and takes)

On Datasets

The traditional datasets for graph learning have been useful (Morris et al., 2020), but in the case where we want to asses either a) fully topological (not only combinatorial) tasks and b) a mixture of topological/geometrical tasks there are just no good options out there. Can we really say we are doing better if we can’t meassure good ?

2020

1. Tudataset: A collection of benchmark datasets for learning with graphs

   Christopher Morris, Nils M Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, and 1 more author

   arXiv preprint arXiv:2007.08663, 2020