One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks. At the same time finding a joint, adaptable representation of data is one of the key challenges in the multi-task learning setting. In this paper, we take a closer look at the relationship between disentanglement and multi-task learning based on hard parameter sharing. We perform a thorough empirical study of the representations obtained by neural networks trained on automatically generated supervised tasks. Using a set of standard metrics we show that disentanglement appears naturally during the process of multi-task neural network training.
@article{arxiv.2110.03498,
title = {On the relationship between disentanglement and multi-task learning},
author = {Łukasz Maziarka and Aleksandra Nowak and Maciej Wołczyk and Andrzej Bedychaj},
journal= {arXiv preprint arXiv:2110.03498},
year = {2021}
}