Scalable Hierarchical Over-the-Air Federated Learning
This addresses scalability and interference challenges in federated learning for wireless networks, though it appears incremental as an extension of hierarchical methods.
The paper tackles scalability, interference, and data heterogeneity in hierarchical federated learning over wireless networks by introducing a two-level learning method with over-the-air aggregation and bandwidth-limited broadcast. It shows the algorithm achieves high learning accuracy and significantly outperforms conventional hierarchical learning.
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 new two-level learning method designed to address these challenges, along with a scalable over-the-air aggregation scheme for the uplink and a bandwidth-limited broadcast scheme for the downlink that efficiently use a single wireless resource. To provide resistance against data heterogeneity, we employ gradient aggregations. Meanwhile, the impact of uplink and downlink interference is minimized through optimized receiver normalizing factors. We present a comprehensive mathematical approach to derive the convergence bound for the proposed algorithm, applicable to a multi-cluster wireless network encompassing any count of collaborating clusters, and provide special cases and design remarks. As a key step to enable a tractable analysis, we develop a spatial model for the setup by modeling devices as a Poisson cluster process over the edge servers and rigorously quantify uplink and downlink error terms due to the interference. Finally, we show that despite the interference and data heterogeneity, the proposed algorithm not only achieves high learning accuracy for a variety of parameters but also significantly outperforms the conventional hierarchical learning algorithm.