Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling

Abstract

This paper proposes a latent space energy-based prior model for semi-supervised learning. The model stands on a generator network that maps a latent vector to the observed example. The energy term of the prior model couples the latent vector and a symbolic one-hot vector, so that classification can be based on the latent vector inferred from the observed example. In our learning method, the symbol-vector coupling, the generator network and the inference network are learned jointly. Our method is applicable to semi-supervised learning in various data domains such as image, text, and tabular data. Our experiments demonstrate that our method performs well on semi-supervised learning tasks.

arXiv commentwork in progress

References in corpus (13)

• Auto-Encoding Variational Bayes
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• Wide Residual Networks
• Temporal Ensembling for Semi-Supervised Learning
• NICE: Non-linear Independent Components Estimation
• Density estimation using Real NVP
• Triple Generative Adversarial Nets
• A Theory of Generative ConvNet
• Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model
• Language GANs Falling Short
• Semi-Supervised Learning with Normalizing Flows
• Learning Latent Space Energy-Based Prior Model

Cited by in corpus (2)

• Trajectory Prediction with Latent Belief Energy-Based Model
• Learning Latent Space Energy-Based Prior Model