Home | Publications | KSS+25a

On Incorporating Scale Into Graph Networks

MCML Authors

Link to Profile Daniel Cremers

Daniel Cremers

Prof. Dr.

Director

Computer Vision & Artificial Intelligence

Abstract

Standard graph neural networks assign vastly different latent embeddings to graphs describing the same physical system at different resolution scales. This precludes consistency in applications and prevents generalization between scales as would fundamentally be needed in many scientific applications. We uncover the underlying obstruction, investigate its origin and show how to overcome it.

inproceedings KSS+25a

MLMP @ICLR 2025

Workshop on Machine Learning Multiscale Processes at the 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. Best Paper Award.

Authors

C. Koke • Y. Shen • A. Saroha • M. Eisenberger • B. Rieck • M. M. Bronstein • D. Cremers

Links

URL

Research Area

 B1 | Computer Vision

BibTeXKey: KSS+25a

#p-cremers #p-wang-xi
Back to Top