FLOSS: Federated Learning with Opt-Out and Straggler Support

TL;DR

FLOSS is a federated learning system designed to handle user opt-outs and device heterogeneity, reducing bias and maintaining model performance despite missing data.

Contribution

The paper introduces FLOSS, a novel system that addresses missing data due to user opt-outs and stragglers in federated learning, improving robustness.

Findings

FLOSS effectively mitigates bias caused by missing data.

Empirical results show FLOSS maintains model accuracy with high opt-out rates.

FLOSS outperforms baseline methods in heterogeneous device scenarios.

Abstract

Previous work on data privacy in federated learning systems focuses on privacy-preserving operations for data from users who have agreed to share their data for training. However, modern data privacy agreements also empower users to use the system while opting out of sharing their data as desired. When combined with stragglers that arise from heterogeneous device capabilities, the result is missing data from a variety of sources that introduces bias and degrades model performance. In this paper, we present FLOSS, a system that mitigates the impacts of such missing data on federated learning in the presence of stragglers and user opt-out, and empirically demonstrate its performance in simulations.