On the Impact of Device and Behavioral Heterogeneity in Federated Learning
This work addresses the challenge of heterogeneity in federated learning systems, which is critical for applications like IoT and recommendation services, but it is incremental as it focuses on characterization rather than proposing new solutions.
The paper investigates how device and behavioral heterogeneity affect model performance and fairness in federated learning, based on an empirical study of nearly 1,500 configurations across five benchmarks.
Federated learning (FL) is becoming a popular paradigm for collaborative learning over distributed, private datasets owned by non-trusting entities. FL has seen successful deployment in production environments, and it has been adopted in services such as virtual keyboards, auto-completion, item recommendation, and several IoT applications. However, FL comes with the challenge of performing training over largely heterogeneous datasets, devices, and networks that are out of the control of the centralized FL server. Motivated by this inherent setting, we make a first step towards characterizing the impact of device and behavioral heterogeneity on the trained model. We conduct an extensive empirical study spanning close to 1.5K unique configurations on five popular FL benchmarks. Our analysis shows that these sources of heterogeneity have a major impact on both model performance and fairness, thus sheds light on the importance of considering heterogeneity in FL system design.