Infinite Variational Autoencoder for Semi-Supervised Learning
This addresses the challenge of semi-supervised learning with small datasets, though it appears incremental as it builds on existing VAE and mixture model techniques.
The paper tackled the problem of adapting model capacity to input data by introducing an infinite variational autoencoder (VAE) that uses a Dirichlet process mixture to automatically vary the number of autoencoders, showing flexibility in semi-supervised learning with limited training samples.
This paper presents an infinite variational autoencoder (VAE) whose capacity adapts to suit the input data. This is achieved using a mixture model where the mixing coefficients are modeled by a Dirichlet process, allowing us to integrate over the coefficients when performing inference. Critically, this then allows us to automatically vary the number of autoencoders in the mixture based on the data. Experiments show the flexibility of our method, particularly for semi-supervised learning, where only a small number of training samples are available.