Good Semi-supervised VAE Requires Tighter Evidence Lower Bound

Haozhe Feng, Kezhi Kong, Tianye Zhang, Siyue Xue, Wei Chen

TL;DR: we propose OSPOT-VAE, a one-stage deep generative model that unifies the generation and classification loss in one ELBO framework and achieves a tighter ELBO.

Abstract: Semi-supervised learning approaches based on generative models have now encountered 3 challenges: (1) The two-stage training strategy is not robust. (2) Good semi-supervised learning results and good generative performance can not be obtained at the same time. (3) Even at the expense of sacrificing generative performance, the semi-supervised classification results are still not satisfactory. To address these problems, we propose One-stage Semi-suPervised Optimal Transport VAE (OSPOT-VAE), a one-stage deep generative model that theoretically unifies the generation and classification loss in one ELBO framework and achieves a tighter ELBO by applying the optimal transport scheme to the distribution of latent variables. We show that with tighter ELBO, our OSPOT-VAE surpasses the best semi-supervised generative models by a large margin across many benchmark datasets. For example, we reduce the error rate from 14.41% to 6.11% on Cifar-10 with 4k labels and achieve state-of-the-art performance with 25.30% on Cifar-100 with 10k labels. We also demonstrate that good generative models and semi-supervised results can be achieved simultaneously by OSPOT-VAE.

Code: https://github.com/PaperCodeSubmission/OSPOT-VAE

Keywords: VAE, Semi-supervised Learning, ELBO, Generative Model