Lancaster University Leipzig is proud to share that research co-authored by our lecturer in Data Science Dr Pascal Welke has been presented at the International Conference on Machine Learning (ICML) 2025 in Vancouver, Canada.
The paper, titled “WILTing Trees: Interpreting the Distance Between MPNN Embeddings,” was authored by Masahiro Negishi, Thomas Gärtner, and Pascal Welke.
This work shows 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.
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning.
Lancaster University Leipzig congratulates Dr Pascal Welke and his co-authors on their contribution to this prestigious venue and their advancement of interpretable machine learning.
