Conditional Neural Relational Inference for Interacting Systems
Abstract
In this work, we want to learn to model the dynamics of similar yet distinct groups of interacting objects. These groups follow some common physical laws that exhibit specificities that are captured through some vectorial description. We develop a model that allows us to do conditional generation from any such group given its vectorial description. Unlike previous work on learning dynamical systems that can only do trajectory completion and require a part of the trajectory dynamics to be provided as input in generation time, we do generation using only the conditioning vector with no access to generation time's trajectories. We evaluate our model in the setting of modeling human gait and, in particular pathological human gait.
Cite
Text
Ramos et al. "Conditional Neural Relational Inference for Interacting Systems." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021. doi:10.1007/978-3-030-86517-7_12Markdown
[Ramos et al. "Conditional Neural Relational Inference for Interacting Systems." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021.](https://mlanthology.org/ecmlpkdd/2021/ramos2021ecmlpkdd-conditional/) doi:10.1007/978-3-030-86517-7_12BibTeX
@inproceedings{ramos2021ecmlpkdd-conditional,
title = {{Conditional Neural Relational Inference for Interacting Systems}},
author = {Ramos, Joao A. Candido and Blondé, Lionel and Armand, Stéphane and Kalousis, Alexandros},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2021},
pages = {182-197},
doi = {10.1007/978-3-030-86517-7_12},
url = {https://mlanthology.org/ecmlpkdd/2021/ramos2021ecmlpkdd-conditional/}
}