Semi-supervised Sequential Generative Models
This work addresses a semi-supervised learning problem for time-series data with discrete latents, which is incremental as it builds upon existing methods like wake-sleep.
The paper tackles the challenge of training deep generative time-series models with discrete latent variables under sparse supervision, introducing a method called caffeinated wake-sleep (CWS) that is robust to variable label frequencies and demonstrates effectiveness on datasets like MNIST, handwriting, and fruit fly trajectories.
We introduce a novel objective for training deep generative time-series models with discrete latent variables for which supervision is only sparsely available. This instance of semi-supervised learning is challenging for existing methods, because the exponential number of possible discrete latent configurations results in high variance gradient estimators. We first overcome this problem by extending the standard semi-supervised generative modeling objective with reweighted wake-sleep. However, we find that this approach still suffers when the frequency of available labels varies between training sequences. Finally, we introduce a unified objective inspired by teacher-forcing and show that this approach is robust to variable length supervision. We call the resulting method caffeinated wake-sleep (CWS) to emphasize its additional dependence on real data. We demonstrate its effectiveness with experiments on MNIST, handwriting, and fruit fly trajectory data.