Improving VAE-based Representation Learning
This addresses the issue of improving representation quality for downstream tasks in machine learning, but it is incremental as it builds on existing VAE structures.
The paper tackled the problem of VAE-based representation learning being less competitive for downstream tasks like semantic classification by showing that using a decoder that prefers local features allows the latent to capture global features, significantly improving classification performance and data efficiency in semi-supervised learning.
Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images. However, for downstream tasks like semantic classification, the representations learned by VAE are less competitive than other non-latent variable models. This has led to some speculations that latent variable models may be fundamentally unsuitable for representation learning. In this work, we study what properties are required for good representations and how different VAE structure choices could affect the learned properties. We show that by using a decoder that prefers to learn local features, the remaining global features can be well captured by the latent, which significantly improves performance of a downstream classification task. We further apply the proposed model to semi-supervised learning tasks and demonstrate improvements in data efficiency.