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.

Cite

Text

Pang et al. "Semi-Supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling." NeurIPS 2020 Workshops: ICBINB, 2020.

Markdown

[Pang et al. "Semi-Supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling." NeurIPS 2020 Workshops: ICBINB, 2020.](https://mlanthology.org/neuripsw/2020/pang2020neuripsw-semisupervised/)

BibTeX

@inproceedings{pang2020neuripsw-semisupervised,
  title     = {{Semi-Supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling}},
  author    = {Pang, Bo and Nijkamp, Erik and Cui, Jiali and Han, Tian and Wu, Ying Nian},
  booktitle = {NeurIPS 2020 Workshops: ICBINB},
  year      = {2020},
  url       = {https://mlanthology.org/neuripsw/2020/pang2020neuripsw-semisupervised/}
}