We are excited to announce that the papers "On the Two Sides of Redundancy in Graph Neural Networks" by Franka Bause, Samir Moustafa, Johannes Langguth, Wilfried N. Gansterer, Nils M. Kriege and "Approximating the Graph Edit Distance with Compact Neighborhood Representations" by Franka Bause, Christian Permann, Nils M. Kriege have been accepted at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2024) with an acceptance rate of ~24%.
Have a look at our papers to learn how to represent node neighborhoods by compact tree structures and how to use them for graph learning and efficient approximation algorithms. We explore the derived computational
graph of graph neural networks and investigate the effect on message-passing redundancy. To approximate the graph edit distance, we develop efficient tree-matching algorithms, from which edit operations are obtained via optimal node assignments.
