Hierarchical Over-the-Air Federated Learning with Awareness of Interference and Data Heterogeneity
This work addresses scalability and robustness issues in federated learning for wireless networks, which is incremental as it builds on existing hierarchical approaches.
The paper tackles the challenges of interference and data heterogeneity in hierarchical federated learning over wireless networks by introducing a method with a scalable transmission scheme using over-the-air computation, achieving high learning accuracy and outperforming conventional hierarchical algorithms.
When implementing hierarchical federated learning over wireless networks, scalability assurance and the ability to handle both interference and device data heterogeneity are crucial. This work introduces a learning method designed to address these challenges, along with a scalable transmission scheme that efficiently uses a single wireless resource through over-the-air computation. To provide resistance against data heterogeneity, we employ gradient aggregations. Meanwhile, the impact of interference is minimized through optimized receiver normalizing factors. For this, we model a multi-cluster wireless network using stochastic geometry, and characterize the mean squared error of the aggregation estimations as a function of the network parameters. We show that despite the interference and the data heterogeneity, the proposed scheme achieves high learning accuracy and can significantly outperform the conventional hierarchical algorithm.