Conference item icon

Conference item

Graph-coupled oscillator networks

Abstract:
We propose Graph-Coupled Oscillator Networks (GraphCON), a novel framework for deep learning on graphs. It is based on discretizations of a second-order system of ordinary differential equations (ODEs), which model a network of nonlinear controlled and damped oscillators, coupled via the adjacency structure of the underlying graph. The flexibility of our framework permits any basic GNN layer (e.g. convolutional or attentional) as the coupling function, from which a multi-layer deep neural network is built up via the dynamics of the proposed ODEs. We relate the oversmoothing problem, commonly encountered in GNNs, to the stability of steady states of the underlying ODE and show that zero-Dirichlet energy steady states are not stable for our proposed ODEs. This demonstrates that the proposed framework mitigates the oversmoothing problem. Moreover, we prove that GraphCON mitigates the exploding and vanishing gradients problem to facilitate training of deep multi-layer GNNs. Finally, we show that our approach offers competitive performance with respect to the state-of-the-art on a variety of graph-based learning tasks.
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publication website:
https://proceedings.mlr.press/v162/rusch22a.html

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Oxford college:
Exeter College
Role:
Author


Publisher:
Journal of Machine Learning Research
Host title:
Proceedings of the 39th International Conference on Machine Learning
Pages:
18888-18909
Series:
Proceedings of Machine Learning Research
Series number:
162
Publication date:
2022-06-28
Event title:
39th International Conference on Machine Learning (ICML 2022)
Event location:
Baltimore, Maryland, USA
Event website:
https://icml.cc/Conferences/2022
Event start date:
2022-07-17
Event end date:
2022-07-23
ISSN:
2640-3498


Language:
English
Keywords:
Pubs id:
1340572
Local pid:
pubs:1340572
Deposit date:
2023-08-08
ARK identifier:

Terms of use


Views and Downloads

Views and downloads will return soon






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP