On the relationship between disentanglement and multi-task learning

Lukasz Maziarka, Aleksandra Nowak, Maciej Wolczyk, Andrzej Bedychaj

Keywords: disentanglement representations, multi-task learning

Abstract: 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 in a natural way during the process of multi-task neural network training.

One-sentence Summary: In our work, we study the relationship between the multi-task learning and disentanglement representations.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2110.03498/code)