The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learning for Interpretable Classification".

Overview

Rule-based Representation Learner

This is a PyTorch implementation of Rule-based Representation Learner (RRL) as described in NeurIPS 2021 paper: Scalable Rule-Based Representation Learning for Interpretable Classification.

drawing

RRL aims to obtain both good scalability and interpretability, and it automatically learns interpretable non-fuzzy rules for data representation and classification. Moreover, RRL can be easily adjusted to obtain a trade-off between classification accuracy and model complexity for different scenarios.

Requirements

  • torch>=1.3.0
  • torchvision>=0.4.1
  • tensorboard>=2.0.0
  • sklearn>=0.22.2.post1
  • numpy>=1.17.2
  • pandas>=0.24.2
  • matplotlib>=3.0.3
  • CUDA==10.1

Run the demo

We need to put the data sets in the dataset folder. You can specify one data set in the dataset folder and train the model as follows:

# trained on the tic-tac-toe data set with one GPU.
python3 experiment.py -d tic-tac-toe -bs 32 -s [email protected] -e401 -lrde 200 -lr 0.002 -ki 0 -mp 12481 -i 0 -wd 1e-6 &

The demo reads the data set and data set information first, then trains the RRL on the training set. During the training, you can check the training loss and the evaluation result on the validation set by:

tensorboard --logdir=log_folder/ --bind_all

drawing

The training log file (log.txt) can be found in a folder created in log_folder. In this example, the folder path is

log_folder/tic-tac-toe/tic-tac-toe_e401_bs32_lr0.002_lrdr0.75_lrde200_wd1[email protected]

After training, the evaluation result on the test set is shown in the file test_res.txt:

[INFO] - On Test Set:
        Accuracy of RRL  Model: 1.0
        F1 Score of RRL  Model: 1.0

Moreover, the trained RRL model is saved in model.pth, and the discrete RRL is printed in rrl.txt:

RID class_negative(b=-2.1733) class_positive(b=1.9689) Support Rule
(-1, 1) -5.8271 6.3045 0.0885 3_x & 6_x & 9_x
(-1, 2) -5.4949 5.4566 0.0781 7_x & 8_x & 9_x
(-1, 4) -4.5605 4.7578 0.1146 1_x & 2_x & 3_x
...... ...... ...... ...... ......

Your own data sets

You can use the demo to train RRL on your own data set by putting the data and data information files in the dataset folder. Please read DataSetDesc for a more specific guideline.

Available arguments

List all the available arguments and their default values by:

$ python3 experiment.py --help
usage: experiment.py [-h] [-d DATA_SET] [-i DEVICE_IDS] [-nr NR] [-e EPOCH]
                     [-bs BATCH_SIZE] [-lr LEARNING_RATE]
                     [-lrdr LR_DECAY_RATE] [-lrde LR_DECAY_EPOCH]
                     [-wd WEIGHT_DECAY] [-ki ITH_KFOLD] [-rc ROUND_COUNT]
                     [-ma MASTER_ADDRESS] [-mp MASTER_PORT] [-li LOG_ITER]
                     [--use_not] [--save_best] [--estimated_grad]
                     [-s STRUCTURE]

optional arguments:
  -h, --help            show this help message and exit
  -d DATA_SET, --data_set DATA_SET
                        Set the data set for training. All the data sets in
                        the dataset folder are available. (default: tic-tac-
                        toe)
  -i DEVICE_IDS, --device_ids DEVICE_IDS
                        Set the device (GPU ids). Split by @. E.g., [email protected]@3.
                        (default: None)
  -nr NR, --nr NR       ranking within the nodes (default: 0)
  -e EPOCH, --epoch EPOCH
                        Set the total epoch. (default: 41)
  -bs BATCH_SIZE, --batch_size BATCH_SIZE
                        Set the batch size. (default: 64)
  -lr LEARNING_RATE, --learning_rate LEARNING_RATE
                        Set the initial learning rate. (default: 0.01)
  -lrdr LR_DECAY_RATE, --lr_decay_rate LR_DECAY_RATE
                        Set the learning rate decay rate. (default: 0.75)
  -lrde LR_DECAY_EPOCH, --lr_decay_epoch LR_DECAY_EPOCH
                        Set the learning rate decay epoch. (default: 10)
  -wd WEIGHT_DECAY, --weight_decay WEIGHT_DECAY
                        Set the weight decay (L2 penalty). (default: 0.0)
  -ki ITH_KFOLD, --ith_kfold ITH_KFOLD
                        Do the i-th 5-fold validation, 0 <= ki < 5. (default:
                        0)
  -rc ROUND_COUNT, --round_count ROUND_COUNT
                        Count the round of experiments. (default: 0)
  -ma MASTER_ADDRESS, --master_address MASTER_ADDRESS
                        Set the master address. (default: 127.0.0.1)
  -mp MASTER_PORT, --master_port MASTER_PORT
                        Set the master port. (default: 12345)
  -li LOG_ITER, --log_iter LOG_ITER
                        The number of iterations (batches) to log once.
                        (default: 50)
  --use_not             Use the NOT (~) operator in logical rules. It will
                        enhance model capability but make the RRL more
                        complex. (default: False)
  --save_best           Save the model with best performance on the validation
                        set. (default: False)
  --estimated_grad      Use estimated gradient. (default: False)
  -s STRUCTURE, --structure STRUCTURE
                        Set the number of nodes in the binarization layer and
                        logical layers. E.g., [email protected], [email protected]@[email protected]. (default:
                        [email protected])

Citation

If our work is helpful to you, please kindly cite our paper as:

@article{wang2021scalable,
  title={Scalable Rule-Based Representation Learning for Interpretable Classification},
  author={Wang, Zhuo and Zhang, Wei and Liu, Ning and Wang, Jianyong},
  journal={arXiv preprint arXiv:2109.15103},
  year={2021}
}

License

MIT license

Owner
Zhuo Wang
Ph.D. student
Zhuo Wang
This repository consists of Blender python scripts and corresponding assets to generate variants of the CANDLE dataset

candle-simulator This repository consists of Blender python scripts and corresponding assets to generate variants of the IITH-CANDLE dataset. The rend

1 Dec 15, 2021
Official implementation of GraphMask as presented in our paper Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking.

GraphMask This repository contains an implementation of GraphMask, the interpretability technique for graph neural networks presented in our ICLR 2021

Michael Schlichtkrull 29 Sep 02, 2022
Small repo describing how to use Hugging Face's Wav2Vec2 with PyCTCDecode

🤗 Transformers Wav2Vec2 + PyCTCDecode Introduction This repo shows how 🤗 Transformers can be used in combination with kensho-technologies's PyCTCDec

Patrick von Platen 102 Oct 22, 2022
Export CenterPoint PonintPillars ONNX Model For TensorRT

CenterPoint-PonintPillars Pytroch model convert to ONNX and TensorRT Welcome to CenterPoint! This project is fork from tianweiy/CenterPoint. I impleme

CarkusL 149 Dec 13, 2022
Fedlearn支持前沿算法研发的Python工具库 | Fedlearn algorithm toolkit for researchers

FedLearn-algo Installation Development Environment Checklist python3 (3.6 or 3.7) is required. To configure and check the development environment is c

89 Nov 14, 2022
Code for "3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop"

PyMAF This repository contains the code for the following paper: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop Hongwe

Hongwen Zhang 450 Dec 28, 2022
A library of extension and helper modules for Python's data analysis and machine learning libraries.

Mlxtend (machine learning extensions) is a Python library of useful tools for the day-to-day data science tasks. Sebastian Raschka 2014-2020 Links Doc

Sebastian Raschka 4.2k Jan 02, 2023
Tree-based Search Graph for Approximate Nearest Neighbor Search

TBSG: Tree-based Search Graph for Approximate Nearest Neighbor Search. TBSG is a graph-based algorithm for ANNS based on Cover Tree, which is also an

Fanxbin 2 Dec 27, 2022
We have made you a wrapper you can't refuse

We have made you a wrapper you can't refuse We have a vibrant community of developers helping each other in our Telegram group. Join us! Stay tuned fo

20.6k Jan 09, 2023
本步态识别系统主要基于GaitSet模型进行实现

本步态识别系统主要基于GaitSet模型进行实现。在尝试部署本系统之前,建立理解GaitSet模型的网络结构、训练和推理方法。 系统的实现效果如视频所示: 演示视频 由于模型较大,部分模型文件存储在百度云盘。 链接提取码:33mb 具体部署过程 1.下载代码 2.安装requirements.txt

16 Oct 22, 2022
Implementation of paper: "Image Super-Resolution Using Dense Skip Connections" in PyTorch

SRDenseNet-pytorch Implementation of paper: "Image Super-Resolution Using Dense Skip Connections" in PyTorch (http://openaccess.thecvf.com/content_ICC

wxy 114 Nov 26, 2022
The comma.ai Calibration Challenge!

Welcome to the comma.ai Calibration Challenge! Your goal is to predict the direction of travel (in camera frame) from provided dashcam video. This rep

comma.ai 697 Jan 05, 2023
Gradient representations in ReLU networks as similarity functions

Gradient representations in ReLU networks as similarity functions by Dániel Rácz and Bálint Daróczy. This repo contains the python code related to our

1 Oct 08, 2021
Python package for multiple object tracking research with focus on laboratory animals tracking.

motutils is a Python package for multiple object tracking research with focus on laboratory animals tracking. Features loads: MOTChallenge CSV, sleap

Matěj Šmíd 2 Sep 05, 2022
Metric learning algorithms in Python

metric-learn: Metric Learning in Python metric-learn contains efficient Python implementations of several popular supervised and weakly-supervised met

1.3k Dec 28, 2022
A PyTorch implementation of unsupervised SimCSE

A PyTorch implementation of unsupervised SimCSE

99 Dec 23, 2022
Code for Active Learning at The ImageNet Scale.

Code for Active Learning at The ImageNet Scale. This repository implements many popular active learning algorithms and allows training with torch's DDP.

Zeyad Emam 47 Dec 12, 2022
Yet another video caption

Yet another video caption

Fan Zhimin 5 May 26, 2022
code for paper "Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?"

Does Unsupervised Architecture Representation Learning Help Neural Architecture Search? Code for paper: Does Unsupervised Architecture Representation

39 Dec 17, 2022
MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions,spherical coordinates, and intensity

MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions,spherical coordinates, and intensity Introduction The 3D LiDAR place recognition aim

16 Dec 08, 2022