Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

Introduction

📋 Official implementation of Explainable Robust Learning MLNThis repository is official im the following paper:

Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

Arxiv

Our contributions are as follows

✔️ We propose a simple yet effective robust learning method leveraging a mixture of experts model on various noise settings.

✔️ The proposed method can not only robustly train from noisy data, but can also provide the explainability by discovering the underlying instance wise noise pattern within the dataset as well the two types of predictive uncertainties(aleatoric and epistemic)

✔️ We present a novel evaluation scheme for validating the set-dependent corruption pattern estimation performance.

Objective

Architecture

Requirements

torch==1.7.1
torchvision==0.8.2
matplotlib==3.4.1
scikit-learn==0.24.1
gensim==4.0.1
scipy==1.6.2
seaborn==0.11.1
Pillow==8.2.0

Datasets

Please download mannually TREC dataset

TREC TREC

Reproducing results of the paper

e.g., mnist on class conditional noise setting

mkdir ckpt
mkdir res
cd scripts
./ccn_mnist.sh

💡 Class Conditional Noise

CIFAR10

Noise Transition Matrix on CIFAR10

💡 Set Dependent Noise

aleatoric uncertainty for the ambiguous set is higher than the clean set and larger for more label noise rate.

estimated noise transition matrix for partioned sets are:

Citing our paper

If you find this work useful please consider citing it:

@article{papername,
  title={title},
  author={authors},
  journal={arXiv preprint arXiv:xxxx.xxxxx},
  year={2021}
}