Cyclical Annealing Schedule: A Simple Approach to Mitigate KL Vanishing

Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. The VAE objective consists of two terms, (i) reconstruction and (ii) KL regularization, balanced by a weighting hyper-parameter β. One notorious training difficulty is that the KL term tends to vanish. In this paper we study scheduling schemes for β, and show that KL vanishing is caused by the lack of good latent codes in training the decoder at the beginning of optimization.

To remedy this, we propose a cyclical annealing schedule, which repeats the process of increasing β multiple times. This new procedure allows the progressive learning of more meaningful latent codes, by leveraging the results of previous learning cycles as warm re-starts. The effectiveness of cyclical annealing is validated on a broad range of NLP tasks, including language modeling, dialog response generation and semi-supervised text classification.

Code: https://github.com/haofuml/cyclical_annealing (opens in new tab)