Federated Learning Meets Fairness and Differential Privacy

08/23/2021

∙

by Manisha Padala, et al.

∙

IIIT Hyderabad

∙

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.

READ FULL TEXT

Federated Learning Meets Fairness and Differential Privacy

Enforcing fairness in private federated learning via the modified method of differential multipliers

Federated Graph Contrastive Learning

LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy

FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations

On Differential Privacy for Federated Learning in Wireless Systems with Multiple Base Stations

Beyond privacy regulations: an ethical approach to data usage in transportation

Local Differential Privacy based Federated Learning for Internet of Things

Federated Learning Meets Fairness and Differential Privacy

Related Research

Enforcing fairness in private federated learning via the modified method of differential multipliers

Federated Graph Contrastive Learning

LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy

FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations

On Differential Privacy for Federated Learning in Wireless Systems with Multiple Base Stations

Beyond privacy regulations: an ethical approach to data usage in transportation

Local Differential Privacy based Federated Learning for Internet of Things