Cyclical annealing schedule: A simple approach to mitigating KL vanishing

Hao Fu, Chunyuan Li, Xiaodong Liu, Jianfeng Gao, Asli Celikyilmaz, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

193 Scopus citations

Abstract

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 informative representations of previous 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 unsupervised language pre-training.
Original languageEnglish (US)
Title of host publicationNAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages240-250
Number of pages11
ISBN (Print)9781950737130
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint

Dive into the research topics of 'Cyclical annealing schedule: A simple approach to mitigating KL vanishing'. Together they form a unique fingerprint.

Cite this