One major challenge of disentanglement learning with variational autoencoders is the trade-off between disentanglement and reconstruction fidelity. Previous incremental methods with only on latent space cannot optimize these two targets simultaneously, so they expand the Information Bottleneck while training to {optimize from disentanglement to reconstruction. However, a large bottleneck will lose the constraint of disentanglement, causing the information diffusion problem. To tackle this issue, we present a novel decremental variational autoencoder with disentanglement-invariant transformations to optimize multiple objectives in different layers, termed DeVAE, for balancing disentanglement and reconstruction fidelity by decreasing the information bottleneck of diverse latent spaces gradually. Benefiting from the multiple latent spaces, DeVAE allows simultaneous optimization of multiple objectives to optimize reconstruction while keeping the constraint of disentanglement, avoiding information diffusion. DeVAE is also compatible with large models with high-dimension latent space. Experimental results on dSprites and Shapes3D that DeVAE achieves \fix{R2q6}{a good balance between disentanglement and reconstruction.DeVAE shows high tolerant of hyperparameters and on high-dimensional latent spaces.

翻译：变分自编码器在解耦学习中的一大挑战是解耦性与重建保真度之间的权衡。以往仅在单一隐空间上操作的增量方法无法同时优化这两个目标，因此它们在训练过程中扩展信息瓶颈，以从解耦优化转向重建优化。然而，过大的瓶颈会失去对解耦的约束，导致信息扩散问题。为解决这一问题，我们提出了一种新颖的递减变分自编码器，通过解耦不变变换在不同层中优化多个目标，称为DeVAE，通过逐步减小多样隐空间的信息瓶颈来平衡解耦性与重建保真度。得益于多个隐空间，DeVAE能够同时优化多个目标，从而在保持解耦约束的同时优化重建，避免信息扩散。DeVAE还与具有高维隐空间的大模型兼容。在dSprites和Shapes3D上的实验结果表明，DeVAE在解耦性与重建之间取得了良好平衡。DeVAE对超参数具有高容忍度，并适用于高维隐空间。