FLOSS: Federated Learning with Opt-Out and Straggler Support
It addresses data privacy and system reliability issues in federated learning for users and developers, but is incremental as it builds on existing federated learning frameworks.
The paper tackles the problem of missing data in federated learning due to user opt-out and stragglers, which introduces bias and degrades model performance, and presents FLOSS to mitigate these impacts, demonstrating its effectiveness in simulations.
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.