Infinite Variational Autoencoder for Semi-Supervised Learning

2016/11/23 by Ehsan Abbasnejad, Abbasnejad, Ehsan, Anthony Dick +3 · 2 citations
Computer Science · #Bayesian Methods and Mixture Models #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1611.07800

openalex publication_date 2016/11/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Semi-Supervised Learning under General Causal Models
• Variational Auto Encoder Gradient Clustering

Related

• Lifelong Mixture of Variational Autoencoders
• Augmenting Variational Autoencoders with Sparse Labels: A Unified Framework for Unsupervised, Semi-(un)supervised, and Supervised Learning
• Tutorial on Variational Autoencoders
• Autoencoding Variational Autoencoder
• Three Variations on Variational Autoencoders