Graph Networks Struggle With Variable Scale
Christian Koke ⋅ Yuesong Shen ⋅ Abhishek Saroha ⋅ Marvin Eisenberger ⋅ Bastian Rieck ⋅ Michael Bronstein ⋅ Daniel Cremers
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.
Chat is not available.
Successful Page Load