Graph Networks Struggle with Variable Scale
Abstract
Standard graph neural networks assign vastly different latent embeddings to graphs describing the same object at different resolution scales. This precludes consistency in applications and prevents generalization between scales as would fundamentally be needed e.g. in AI4Science. We uncover the underlying obstruction, investigate its origin and show how to overcome it by modifying the message passing paradigm.
Cite
Text
Koke et al. "Graph Networks Struggle with Variable Scale." ICLR 2025 Workshops: ICBINB, 2025.Markdown
[Koke et al. "Graph Networks Struggle with Variable Scale." ICLR 2025 Workshops: ICBINB, 2025.](https://mlanthology.org/iclrw/2025/koke2025iclrw-graph/)BibTeX
@inproceedings{koke2025iclrw-graph,
title = {{Graph Networks Struggle with Variable Scale}},
author = {Koke, Christian and Shen, Yuesong and Saroha, Abhishek and Eisenberger, Marvin and Rieck, Bastian and Bronstein, Michael M. and Cremers, Daniel},
booktitle = {ICLR 2025 Workshops: ICBINB},
year = {2025},
url = {https://mlanthology.org/iclrw/2025/koke2025iclrw-graph/}
}