Skip to content

Increasing Robustness to Spurious Correlations using Attention Regularization

License

Notifications You must be signed in to change notification settings

chandar-lab/EAT

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Should we attend more or less? Modulating attention for fairness (COLM 2024)

This is the official repository for Should we attend more or less? Modulating attention for fairness, accepted at COLM 2024.

Summary: We show that bias can be mitigated by focusing on a wider/narrower context.

Usage

Please follow the instructions in our tutorial.

Citation

@article{zayed2023should,
  title={Should we attend more or less? modulating attention for fairness},
  author={Zayed, Abdelrahman and Mordido, Goncalo and Shabanian, Samira and Chandar, Sarath},
  journal={arXiv preprint arXiv:2305.13088},
  year={2023}
}

About

Increasing Robustness to Spurious Correlations using Attention Regularization

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published