Sequential variational autoencoders (VAEs) with a global latent variable z have been studied for disentangling the global features of data, which is useful for several downstream tasks. To further assist the sequential VAEs in obtaining meaningful z, existing approaches introduce a regularization term that maximizes the mutual information (MI) between the observation and z. However, by analyzing the sequential VAEs from the information-theoretic perspective, we claim that simply maximizing the MI encourages the latent variable to have redundant information, thereby preventing the disentanglement of global features. Based on this analysis, we derive a novel regularization method that makes z informative while encouraging disentanglement. Specifically, the proposed method removes redundant information by minimizing the MI between z and the local features by using adversarial training. In the experiments, we trained two sequential VAEs, state-space and autoregressive model variants, using speech and image datasets. The results indicate that the proposed method improves the performance of downstream classification and data generation tasks, thereby supporting our information-theoretic perspective for the learning of global features.

已经研究了具有全局潜在变量z 的顺序变分自编码器 (VAE) 以解开数据的全局特征，这对多个下游任务很有用。为了进一步帮助顺序 VAE 获得有意义的z，现有方法引入了一个正则化项，该项可以最大化观察和z之间的互信息 (MI) 。然而，通过从信息理论的角度分析顺序 VAE，我们声称简单地最大化 MI 会鼓励潜在变量具有冗余信息，从而防止全局特征的解开。基于此分析，我们推导出一种新的正则化方法，使z信息丰富，同时鼓励解开。具体来说，所提出的方法通过使用对抗训练最小化z和局部特征之间的 MI 来去除冗余信息。在实验中，我们使用语音和图像数据集训练了两个连续的 VAE、状态空间和自回归模型变体。结果表明，所提出的方法提高了下游分类和数据生成任务的性能，从而支持我们学习全局特征的信息论观点。