DynamicVAE: Decoupling Reconstruction Error and Disentangled Representation Learning

Huajie Shao, Haohong Lin, Qinmin Yang, Shuochao Yao, Han Zhao, Tarek Abdelzaher

Keywords: disentangled representation learning, dynamic learning, Variational Autoencoder, PID contoller

Abstract: This paper challenges the common assumption that the weight $\beta$, in $\beta$-VAE, should be larger than $1$ in order to effectively disentangle latent factors. We demonstrate that $\beta$-VAE, with $\beta < 1$, can not only attain good disentanglement but also significantly improve reconstruction accuracy via dynamic control. The paper \textit{removes the inherent trade-off} between reconstruction accuracy and disentanglement for $\beta$-VAE. Existing methods, such as $\beta$-VAE and FactorVAE, assign a large weight to the KL-divergence term in the objective function, leading to high reconstruction errors for the sake of better disentanglement. To mitigate this problem, a ControlVAE has recently been developed that dynamically tunes the KL-divergence weight in an attempt to \textit{control the trade-off} to more a favorable point. However, ControlVAE fails to eliminate the conflict between the need for a large $\beta$ (for disentanglement) and the need for a small $\beta$ (for smaller reconstruction error). Instead, we propose DynamicVAE that maintains a different $\beta$ at different stages of training, thereby \textit{decoupling disentanglement and reconstruction accuracy}. In order to evolve the weight, $\beta$, along a trajectory that enables such decoupling, DynamicVAE leverages a modified incremental PI (proportional-integral) controller, a variant of proportional-integral-derivative controller (PID) algorithm, and employs a moving average as well as a hybrid annealing method to evolve the value of KL-divergence smoothly in a tightly controlled fashion. We theoretically prove the stability of the proposed approach. Evaluation results on three benchmark datasets demonstrate that DynamicVAE significantly improves the reconstruction accuracy while achieving disentanglement comparable to the best of existing methods. The results verify that our method can separate disentangled representation learning and reconstruction, removing the inherent tension between the two.

One-sentence Summary: The goal of this paper is to decouple disentangling and reconstruction for disentangled representation learning via dynamic control.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=K2C8frX-O4