We show that message passing neural networks (MPNNs) are implicitly trained to respect graph functional distances, and introduce the weighted Weisfeiler Leman Labeling Tree (WILT) to identify subgraphs that MPNNs consider functionally important.
Pascal Welke
@pascalwelke.bsky.social
144 followers 78 following 15 posts
Graph Machine Learning and Graph Mining Assistant Professor (Lecturer) in Data Science Lancaster University Leipzig pwelke.de
