Deep Networks from the Principle of Rate Reduction
This repository is the official PyTorch implementation of the paper Deep Networks from the Principle of Rate Reduction (2021) by Kwan Ho Ryan Chan* (UC Berkeley), Yaodong Yu* (UC Berkeley), Chong You* (UC Berkeley), Haozhi Qi (UC Berkeley), John Wright (Columbia), and Yi Ma (UC Berkeley). For the NumPy version of ReduNet, please go checkout: https://github.com/ryanchankh/redunet_paper
What is ReduNet?
ReduNet is a deep neural network construcuted naturally by deriving the gradients of the Maximal Coding Rate Reduction (MCR2) [1] objective. Every layer of this network can be interpreted based on its mathematical operations and the network collectively is trained in a feed-forward manner only. In addition, by imposing shift invariant properties to our network, the convolutional operator can be derived using only the data and MCR2 objective function, hence making our network design principled and interpretable.
Figure: Weights and operations for one layer of ReduNet
[1] Yu, Yaodong, Kwan Ho Ryan Chan, Chong You, Chaobing Song, and Yi Ma. "Learning diverse and discriminative representations via the principle of maximal coding rate reduction" Advances in Neural Information Processing Systems 33 (2020).
Requirements
This codebase is written for python3. To install necessary python packages, run conda create --name redunet_official --file requirements.txt.
Demo
For a quick demonstration of ReduNet on Gaussian 2D or 3D cases, please visit the notebook by running one of the two commands:
$ jupyter notebook ./examples/gaussian2d.ipynb
$ jupyter notebook ./examples/gaussian3d.ipynb
Core Usage and Design
The design of this repository aims to be easy-to-use and easy-to-intergrate to the current framework of your experiment, as long as it uses PyTorch. The ReduNet object inherents from nn.Sequential, and layers ReduLayers, such as Vector, Fourier1D and Fourier2D inherent from nn.Module. Loss functions are implemented in loss.py. Architectures and Dataset options are located in load.py file. Data objects and pre-set architectures are loaded in folders dataset and architectures. Feel free to add more based on the experiments you want to run. We have provided basic experiment setups, located in train_ and evaluate_, where functional.py or utils.py. Feel free to email us if there are any issues or suggestions.
Example: Forward Construction
To train a ReduNet using forward construction, please checkout train_forward.py. For evaluating, please checkout evaluate_forward.py. For example, to train on 40-layer ReduNet on MNIST using 1000 samples per class, run:
$ python3 train_forward.py --data mnistvector --arch layers50 --samples 1000
After training, you can evaluate the trained model using evaluate_forward.py, by running:
$ python3 evaluate_forward.py --model_dir ./saved_models/forward/mnistvector+layers50/samples1000
, which will evaluate using all available training samples and testing samples. For more training and testing options, please checkout the file train_forward.py and evaluate_forward.py.
Experiments in Paper
For code used to generate experimental empirical results listed in our paper, please visit our other repository: https://github.com/ryanchankh/redunet_paper
Reference
For technical details and full experimental results, please check the paper. Please consider citing our work if you find it helpful to yours:
@article{chan2020deep,
title={Deep networks from the principle of rate reduction},
author={Chan, Kwan Ho Ryan and Yu, Yaodong and You, Chong and Qi, Haozhi and Wright, John and Ma, Yi},
journal={arXiv preprint arXiv:2010.14765},
year={2020}
}
License and Contributing
- This README is formatted based on paperswithcode.
- Feel free to post issues via Github.
Contact
Please contact [email protected] and [email protected] if you have any question on the codes.
39 Dec 24, 2022
42 Nov 25, 2022
36 Sep 14, 2022
137 Dec 13, 2022
105 Dec 28, 2022
4 Dec 27, 2022
11 Nov 15, 2022
84 Jan 4, 2023
150 Dec 23, 2022
4 Jun 21, 2022
3 Aug 24, 2022
42 Nov 24, 2022
109 Dec 23, 2022
59 Dec 8, 2022
370 Dec 27, 2022
16 Nov 26, 2022
52 Nov 14, 2022
37 Oct 30, 2022
3 Nov 4, 2022