Federated Learning Can Find Friends That Are Advantageous
This addresses the challenge of client heterogeneity in Federated Learning, offering a more efficient implementation, though it is incremental as it builds on existing FL methods.
The paper tackles the problem of detrimental collaborations in Federated Learning by introducing an algorithm that assigns adaptive aggregation weights to clients, identifying those with beneficial data distributions. It demonstrates convergence no worse than methods using only similar clients and shows empirical outperformance over traditional approaches.
In Federated Learning (FL), the distributed nature and heterogeneity of client data present both opportunities and challenges. While collaboration among clients can significantly enhance the learning process, not all collaborations are beneficial; some may even be detrimental. In this study, we introduce a novel algorithm that assigns adaptive aggregation weights to clients participating in FL training, identifying those with data distributions most conducive to a specific learning objective. We demonstrate that our aggregation method converges no worse than the method that aggregates only the updates received from clients with the same data distribution. Furthermore, empirical evaluations consistently reveal that collaborations guided by our algorithm outperform traditional FL approaches. This underscores the critical role of judicious client selection and lays the foundation for more streamlined and effective FL implementations in the coming years.