Neural Relational Inference for Interacting Systems

Thomas Kipf, Ethan Fetaya, Kuan-Chieh Wang, Max Welling, Richard Zemel
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:2688-2697, 2018.

Abstract

Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics. The interplay of components can give rise to complex behavior, which can often be explained using a simple model of the system’s constituent parts. In this work, we introduce the neural relational inference (NRI) model: an unsupervised model that learns to infer interactions while simultaneously learning the dynamics purely from observational data. Our model takes the form of a variational auto-encoder, in which the latent code represents the underlying interaction graph and the reconstruction is based on graph neural networks. In experiments on simulated physical systems, we show that our NRI model can accurately recover ground-truth interactions in an unsupervised manner. We further demonstrate that we can find an interpretable structure and predict complex dynamics in real motion capture and sports tracking data.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-kipf18a, title = {Neural Relational Inference for Interacting Systems}, author = {Kipf, Thomas and Fetaya, Ethan and Wang, Kuan-Chieh and Welling, Max and Zemel, Richard}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {2688--2697}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/kipf18a/kipf18a.pdf}, url = {https://proceedings.mlr.press/v80/kipf18a.html}, abstract = {Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics. The interplay of components can give rise to complex behavior, which can often be explained using a simple model of the system’s constituent parts. In this work, we introduce the neural relational inference (NRI) model: an unsupervised model that learns to infer interactions while simultaneously learning the dynamics purely from observational data. Our model takes the form of a variational auto-encoder, in which the latent code represents the underlying interaction graph and the reconstruction is based on graph neural networks. In experiments on simulated physical systems, we show that our NRI model can accurately recover ground-truth interactions in an unsupervised manner. We further demonstrate that we can find an interpretable structure and predict complex dynamics in real motion capture and sports tracking data.} }
Endnote
%0 Conference Paper %T Neural Relational Inference for Interacting Systems %A Thomas Kipf %A Ethan Fetaya %A Kuan-Chieh Wang %A Max Welling %A Richard Zemel %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-kipf18a %I PMLR %P 2688--2697 %U https://proceedings.mlr.press/v80/kipf18a.html %V 80 %X Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics. The interplay of components can give rise to complex behavior, which can often be explained using a simple model of the system’s constituent parts. In this work, we introduce the neural relational inference (NRI) model: an unsupervised model that learns to infer interactions while simultaneously learning the dynamics purely from observational data. Our model takes the form of a variational auto-encoder, in which the latent code represents the underlying interaction graph and the reconstruction is based on graph neural networks. In experiments on simulated physical systems, we show that our NRI model can accurately recover ground-truth interactions in an unsupervised manner. We further demonstrate that we can find an interpretable structure and predict complex dynamics in real motion capture and sports tracking data.
APA
Kipf, T., Fetaya, E., Wang, K., Welling, M. & Zemel, R.. (2018). Neural Relational Inference for Interacting Systems. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:2688-2697 Available from https://proceedings.mlr.press/v80/kipf18a.html.

Related Material