Skip to content
Code for reproducing Manifold Mixup results (ICML 2019)
Python Shell
Branch: master
Clone or download
Latest commit 5485529 Oct 4, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
data zca components Sep 21, 2018
gan Update Dec 14, 2018
supervised Update Oct 3, 2019 Update Jul 17, 2019
hstates_3.png refactored supervised learning subrepo Feb 18, 2019
mmfig1.png Add files via upload Feb 18, 2019
mmfig2.png Add files via upload Feb 18, 2019

Manifold_mixup (ICML 2019)

This repo consists Pytorch code for the ICML 2019 paper Manifold Mixup: Better Representations by Interpolating Hidden States ( ICML version (

The goal of our proposed algorithm, Manifold Mixup, is to learn robust features by interpolating the hidden states of examples. The representations learned by our method are more discriminative and compact as shown in the below figure. Please refer to Figure 1 and Figure 2 of our paper for more details.

The repo consist of two subfolders for Supervised Learning and GAN experiments. Each subfolder is self-contained (can be used independently of the other subfolders). Each subfolder has its own instruction on "How to run" in its file.

If you find this work useful and use it on your own research, please concider citing our paper.

  title = 	 {Manifold Mixup: Better Representations by Interpolating Hidden States},
  author = 	 {Verma, Vikas and Lamb, Alex and Beckham, Christopher and Najafi, Amir and Mitliagkas, Ioannis and Lopez-Paz, David and Bengio, Yoshua},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {6438--6447},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Long Beach, California, USA},
  month = 	 {09--15 Jun},
  publisher = 	 {PMLR},
  pdf = 	 {},
  url = 	 {},

Note: Please refer to our new repo for Interpolation based Semi-supervised Learning

You can’t perform that action at this time.