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:
-
-
(Preview, Version of record, pdf, 572.0KB, Terms of use)
-
- Publication website:
- https://proceedings.mlr.press/v162/rusch22a.html
Authors
- 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
- Copyright holder:
- Rusch et al.
- Copyright date:
- 2022
- Rights statement:
- © The Authors. This is an open access article under a Creative Commons license.
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record