Deep Dive into Semi-Supervised ELBO for Improving Classification Performance
This work addresses a specific bottleneck in semi-supervised learning for researchers, but it is incremental as it builds on existing VAE-based models.
The paper tackled the problem of improving semi-supervised classification with VAE models by analyzing ELBO decomposition, revealing a decrease in mutual information between input and class labels, and proposed a method to address this while enforcing cluster assumption. Experiments on diverse datasets showed improved classification performance without sacrificing generative power, though no concrete numbers were provided.
Decomposition of the evidence lower bound (ELBO) objective of VAE used for density estimation revealed the deficiency of VAE for representation learning and suggested ways to improve the model. In this paper, we investigate whether we can get similar insights by decomposing the ELBO for semi-supervised classification using VAE model. Specifically, we show that mutual information between input and class labels decreases during maximization of ELBO objective. We propose a method to address this issue. We also enforce cluster assumption to aid in classification. Experiments on a diverse datasets verify that our method can be used to improve the classification performance of existing VAE based semi-supervised models. Experiments also show that, this can be achieved without sacrificing the generative power of the model.