Modular Representations for Weak Disentanglement
This addresses a scalability issue in representation learning for AI, though it is incremental as it builds on existing weak disentanglement concepts.
The paper tackles the problem of weak disentanglement requiring increasing supervision with more factors by introducing modular representations, which maintain constant supervision and improve performance over prior work.
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.