Binary concepts are empirically used by humans to generalize efficiently. And they are based on Bernoulli distribution which is the building block of information. These concepts span both low-level and high-level features such as "large vs small" and "a neuron is active or inactive". Binary concepts are ubiquitous features and can be used to transfer knowledge to improve model generalization. We propose a novel binarized regularization to facilitate learning of binary concepts to improve the quality of data generation in autoencoders. We introduce a binarizing hyperparameter $r$ in data generation process to disentangle the latent space symmetrically. We demonstrate that this method can be applied easily to existing variational autoencoder (VAE) variants to encourage symmetric disentanglement, improve reconstruction quality, and prevent posterior collapse without computation overhead. We also demonstrate that this method can boost existing models to learn more transferable representations and generate more representative samples for the input distribution which can alleviate catastrophic forgetting using generative replay under continual learning settings.
翻译:二进制概念是人类经验性地用于有效地进行泛化的概念。它们基于伯努利分布,这是信息的基本构建模块。这些概念涵盖了低级特征和高级特征,例如“大 vs 小”和“神经元是否活跃”。二进制概念是无处不在的特征,可用于转移知识以改善模型泛化能力。我们提出了一种新颖的二值正则化方法,以促进学习二值概念,从而提高自动编码器中数据生成的质量。我们在数据生成过程中引入二值化超参数 $r$ 以对称分离潜在空间。我们证明这种方法可以轻松应用于现有的变分自编码(VAE)变体,以鼓励对称分离,提高重建质量,并防止后验崩溃,而无需计算开销。我们还证明,此方法可以推动现有模型学习更具传递性的表示,并生成更具代表性的样本,以缓解在连续学习设置下通过生成回放进行的灾难性遗忘。