https://github.com/yzhuoning/deepauc

Stochastic AUC Maximization with Deep Neural Networks
https://github.com/yzhuoning/deepauc

auc-roc-score deep-neural-networks optimization

Last synced: about 2 months ago
JSON representation

Stochastic AUC Maximization with Deep Neural Networks

• Host: GitHub
• URL: https://github.com/yzhuoning/deepauc
• Owner: yzhuoning
• Created: 2020-06-17T20:05:44.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2021-04-01T19:03:27.000Z (over 3 years ago)
• Last Synced: 2023-10-20T23:58:35.166Z (about 1 year ago)
• Topics: auc-roc-score, deep-neural-networks, optimization
• Language: Python
• Homepage:
• Size: 24.4 KB
• Stars: 15
• Watchers: 3
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Deep AUC Maximization  [![pdf](https://img.shields.io/badge/Arxiv-pdf-orange.svg?style=flat)](https://arxiv.org/abs/1908.10831)

This is the official implementation of the paper "**Stochastic AUC Maximization with Deep Neural Networks**" published on **ICLR2020**. 

## Installation

```

Python=3.5

Numpy=1.18.5 

Scipy=1.2.1

Scikit-Learn=0.20.3

Pillow=5.0.0

Tensorflow>=1.10.0

```

### Run

```

python PPD_SG.py/PPD_AdaGrad.py --dataset=10 --train_batch_size=128 --use_L2=False --split_index=4 --lr=0.01 --keep_index=0.1 --t0=200

```

### Hyperparameter tuning

```

gamma=[500, 1000, 2000, ...]

eta = [0.1, 0.01, ...]

T0=[1000, 2000, 3000, ...,]

```

## Bibtex 

If you use this repository in your work, please cite our paper:

```

@inproceedings{

Liu2020Stochastic,

title={Stochastic AUC Maximization with Deep Neural Networks},

author={Mingrui Liu and Zhuoning Yuan and Yiming Ying and Tianbao Yang},

booktitle={International Conference on Learning Representations},

year={2020},

url={https://openreview.net/forum?id=HJepXaVYDr}

}

```