Semi-Conditional Normalizing Flows for Semi-Supervised Learning
arXiv:1905.00505
Abstract
This paper proposes a semi-conditional normalizing flow model for semi-supervised learning. The model uses both labelled and unlabeled data to learn an explicit model of joint distribution over objects and labels. Semi-conditional architecture of the model allows us to efficiently compute a value and gradients of the marginal likelihood for unlabeled objects. The conditional part of the model is based on a proposed conditional coupling layer. We demonstrate performance of the model for semi-supervised classification problem on different datasets. The model outperforms the baseline approach based on variational auto-encoders on MNIST dataset.
References in corpus (11)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Conditional Image Generation with PixelCNN Decoders
- Semi-Supervised Learning with Deep Generative Models
- NICE: Non-linear Independent Components Estimation
- Density estimation using Real NVP
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- Variational Bayesian Inference with Stochastic Search
- Sylvester Normalizing Flows for Variational Inference
- DIVA: Domain Invariant Variational Autoencoders
- Conditional Density Estimation with Bayesian Normalising Flows
Cited by in corpus (14)
- Normalizing Flows: An Introduction and Review of Current Methods
- DIVA: Domain Invariant Variational Autoencoders
- CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
- Why Normalizing Flows Fail to Detect Out-of-Distribution Data
- Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
- Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
- SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech
- Semi-Supervised Learning with Normalizing Flows
- Semi-supervised Learning with Missing Values Imputation
- Weakly Supervised Label Learning Flows
- Task-agnostic Continual Learning with Hybrid Probabilistic Models
- Likelihood Contribution based Multi-scale Architecture for Generative Flows
- Robust model training and generalisation with Studentising flows
- Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models