Franka Presents Poster at ECML/PKDD

Franka presented the paper Maximally Expressive GNNs for Outerplanar Graphs by Franka Bause, Fabian Jogl, Patrick Indri, Tamara Drucks, David Penz, Nils Kriege, Thomas Gärtner, Pascal Welke, and Maximilian Thiessen (published at TMLR earlier this year) at the ECML/PKDD 2025 Nectar Track!

Our paper proposes a linear time graph transformation that enables the Weisfeiler-Leman (WL) algorithm and message passing graph neural networks (MPNNs) to be maximally expressive on outerplanar graphs, motivated by the fact that most pharmaceutical molecules correspond to outerplanar graphs.