https://github.com/ermongroup/ssdkl
Code that accompanies the paper Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance
https://github.com/ermongroup/ssdkl
Last synced: 5 months ago
JSON representation
Code that accompanies the paper Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance
- Host: GitHub
- URL: https://github.com/ermongroup/ssdkl
- Owner: ermongroup
- Created: 2018-10-24T08:20:23.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2019-01-22T19:10:57.000Z (over 6 years ago)
- Last Synced: 2025-03-31T16:12:58.163Z (6 months ago)
- Language: Python
- Homepage:
- Size: 113 KB
- Stars: 76
- Watchers: 8
- Forks: 29
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Semi-supervised Deep Kernel Learning
This is the code that accompanies the paper [Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance](https://arxiv.org/abs/1805.10407)
Install via `pip install -e .` in this directory in
a NEW virtualenv.
- Experiments for SSDKL, DKL, VAT, Coreg are in the directory `ssdkl`.
- Experiments for Label Propagation and Mean Teacher are in `labelprop_and_meanteacher`.
- Experiments for VAE are in the directory `vae`.
For more detailed instructions, please see the README files in each directory.
Tested with Python 2.7.12.
If you find this code useful in your research, please cite
```
@article{jeanxieermon_ssdkl_2018,
title={Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance},
author={Jean, Neal and Xie, Sang Michael and Ermon, Stefano},
journal={Neural Information Processing Systems (NIPS)},
year={2018},
}
```