Disentangled Generative Models for Robust Prediction of System Dynamics
Abstract
The use of deep neural networks for modelling system dynamics is increasingly popular, but long-term prediction accuracy and out-of-distribution generalization still present challenges. In this study, we address these challenges by considering the parameters of dynamical systems as factors of variation of the data and leverage their ground-truth values to disentangle the representations learned by generative models. Our experimental results in phase-space and observation-space dynamics, demonstrate the effectiveness of latent-space supervision in producing disentangled representations, leading to improved long-term prediction accuracy and out-of-distribution robustness.
Cite
Text
Fotiadis et al. "Disentangled Generative Models for Robust Prediction of System Dynamics." International Conference on Machine Learning, 2023.Markdown
[Fotiadis et al. "Disentangled Generative Models for Robust Prediction of System Dynamics." International Conference on Machine Learning, 2023.](https://mlanthology.org/icml/2023/fotiadis2023icml-disentangled/)BibTeX
@inproceedings{fotiadis2023icml-disentangled,
title = {{Disentangled Generative Models for Robust Prediction of System Dynamics}},
author = {Fotiadis, Stathi and Lino Valencia, Mario and Hu, Shunlong and Garasto, Stef and Cantwell, Chris D and Bharath, Anil Anthony},
booktitle = {International Conference on Machine Learning},
year = {2023},
pages = {10222-10248},
volume = {202},
url = {https://mlanthology.org/icml/2023/fotiadis2023icml-disentangled/}
}