Skip to content

The official repository for ICLR'23 Paper "Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning"

License

Notifications You must be signed in to change notification settings

NeurAI-Lab/ESMER

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ESMER

Official Repository for ICLR'23 Paper "Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning"

We extended the CLS-ER repo with our method

Setup

  • Use python main.py to run experiments.

  • Use argument --load_best_args to use the best hyperparameters for each of the evaluation setting from the paper.

  • To reproduce the results in the paper run the following

    python main.py --dataset <dataset> --model <model> --buffer_size <buffer_size> --load_best_args

    Examples:

    python main.py --dataset seq-cifar10 --model esmer --buffer_size 200 --load_best_args
    
    python main.py --dataset seq-cifar100 --model esmer --buffer_size 200 --load_best_args
    

    For GCIL-CIFAR-100 Experiments

    python main.py --dataset gcil-cifar100 --weight_dist unif --model esmer --buffer_size 200 --load_best_args
    
    python main.py --dataset gcil-cifar100 --weight_dist longtail --model esmer --buffer_size 200 --load_best_args
    

Requirements

  • torch==1.7.0
  • torchvision==0.9.0

Cite Our Work

If you find the code useful in your research, please consider citing our paper:

@inproceedings{
  sarfrazerror,
  title={Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning},
  author={Sarfraz, Fahad and Arani, Elahe and Zonooz, Bahram},
  booktitle={The Eleventh International Conference on Learning Representations},
  year={2023},
  url={https://openreview.net/forum?id=zlbci7019Z3}
}

About

The official repository for ICLR'23 Paper "Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning"

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages