Federated Learning Meets Fairness and Differential Privacy

Manisha Padala; Sankarshan Damle; Sujit Gujar

Federated Learning Meets Fairness and Differential Privacy

Machine Learning 2021-08-24 v1 Artificial Intelligence Cryptography and Security Computers and Society

Authors: Manisha Padala , Sankarshan Damle , Sujit Gujar

Abstract

Deep learning's unprecedented success raises several ethical concerns ranging from biased predictions to data privacy. Researchers tackle these issues by introducing fairness metrics, or federated learning, or differential privacy. A first, this work presents an ethical federated learning model, incorporating all three measures simultaneously. Experiments on the Adult, Bank and Dutch datasets highlight the resulting ``empirical interplay" between accuracy, fairness, and privacy.

Keywords

distributed learning federated learning fairness in machine learning

Cite

@article{arxiv.2108.09932,
  title  = {Federated Learning Meets Fairness and Differential Privacy},
  author = {Manisha Padala and Sankarshan Damle and Sujit Gujar},
  journal= {arXiv preprint arXiv:2108.09932},
  year   = {2021}
}

Related papers

View all related →