The Variational Homoencoder: Learning to learn high capacity generative models from few examples

Abstract

Hierarchical Bayesian methods can unify many related tasks (e.g. k-shot classification, conditional and unconditional generation) as inference within a single generative model. However, when this generative model is expressed as a powerful neural network such as a PixelCNN, we show that existing learning techniques typically fail to effectively use latent variables. To address this, we develop a modification of the Variational Autoencoder in which encoded observations are decoded to new elements from the same class. This technique, which we call a Variational Homoencoder (VHE), produces a hierarchical latent variable model which better utilises latent variables. We use the VHE framework to learn a hierarchical PixelCNN on the Omniglot dataset, which outperforms all existing models on test set likelihood and achieves strong performance on one-shot generation and classification tasks. We additionally validate the VHE on natural images from the YouTube Faces database. Finally, we develop extensions of the model that apply to richer dataset structures such as factorial and hierarchical categories.

UAI 2018 oral presentation

References in corpus (11)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Conditional Image Generation with PixelCNN Decoders
• DRAW: A Recurrent Neural Network For Image Generation
• Matching Networks for One Shot Learning
• Deep Convolutional Inverse Graphics Network
• Learning to Remember Rare Events
• Towards a Neural Statistician
• Few-Shot Learning Through an Information Retrieval Lens
• Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
• Fast Adaptation in Generative Models with Generative Matching Networks

Cited by in corpus (17)

• Conditional Neural Processes
• Attentive Neural Processes
• Experience-Embedded Visual Foresight
• Few-shot Learning for Time-series Forecasting
• A Meta-Learning Framework for Generalized Zero-Shot Learning
• Meta-Learning surrogate models for sequential decision making
• Meta-Amortized Variational Inference and Learning
• AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning
• A Simple Framework for Uncertainty in Contrastive Learning
• Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation
• Few-shot Learning for Spatial Regression
• Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection
• Meta-Active Learning for Node Response Prediction in Graphs
• Few-shot Learning for Topic Modeling
• OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation
• Meta-learning for Matrix Factorization without Shared Rows or Columns
• Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation