Variational autoencoders (VAEs) are one of the powerful unsupervised learning frameworks in NLP for latent representation learning and latent-directed generation. The classic optimization goal of VAEs is to maximize the Evidence Lower Bound (ELBo), which consists of a conditional likelihood for generation and a negative Kullback-Leibler (KL) divergence for regularization. In practice, optimizing ELBo often leads the posterior distribution of all samples converge to the same degenerated local optimum, namely posterior collapse or KL vanishing. There are effective ways proposed to prevent posterior collapse in VAEs, but we observe that they in essence make trade-offs between posterior collapse and hole problem, i.e., mismatch between the aggregated posterior distribution and the prior distribution. To this end, we introduce new training objectives to tackle both two problems through a novel regularization based on the probabilistic density gap between the aggregated posterior distribution and the prior distribution. Through experiments on language modeling, latent space visualization and interpolation, we show that our proposed method can solve both problems effectively and thus outperforms the existing methods in latent-directed generation. To the best of our knowledge, we are the first to jointly solve the hole problem and the posterior collapse.
翻译:动态自动读数器(VAE)是国家实验室规划中用于潜在代表学习和潜导一代的强大、不受监督的学习框架之一。 VAE的经典优化目标是最大限度地增加证据下下界(ELBo),其中包括生成的有条件可能性和负面的 Kullback-Liber(KL) 差异,以规范化。在实践中,优化 ELBo 常常导致所有样本的后端分布,形成同一退化的本地最佳样本,即后端崩溃或 KL消失。有建议的有效方法防止 VAE 的后端崩溃,但我们认为,从本质上说,它们会在后端崩溃和洞问题之间作出交易,即综合后端分布与先前分布之间的不匹配。为此,我们引入了新的培训目标,通过基于总体后端分布与先前分布之间概率性密度差距的新式的稳妥性调节,解决这两个问题。通过语言模型化、潜潜伏空间视觉化和内置等实验,我们发现,从本质上说,在后端崩溃和前端生成过程中,我们所提议的方法可以有效地解决现有的潜在问题,从而形成后方方法。