Modular Representations for Weak Disentanglement

TL;DR

This paper introduces modular representations for weak disentanglement, enabling models to maintain constant supervision levels while improving performance in capturing data generative factors.

Contribution

The proposed modular approach allows weak disentanglement without increasing supervision as the number of factors grows.

Findings

Models with modular representations outperform previous methods.

Performance improves without additional supervision.

Constant supervision level achieved regardless of factors.

Abstract

The recently introduced weakly disentangled representations proposed to relax some constraints of the previous definitions of disentanglement, in exchange for more flexibility. However, at the moment, weak disentanglement can only be achieved by increasing the amount of supervision as the number of factors of variations of the data increase. In this paper, we introduce modular representations for weak disentanglement, a novel method that allows to keep the amount of supervised information constant with respect the number of generative factors. The experiments shows that models using modular representations can increase their performance with respect to previous work without the need of additional supervision.