Analog-digital Scheduling for Federated Learning: A Communication-Efficient Approach

• Published in: 2023 57th Asilomar Conference on Signals, Systems, and Computers pp. 53 - 58
• Main Authors: Ul Abrar, Muhammad Faraz, Michelusi, Nicolo
• Format: Conference Proceeding
• Language: English
• Published: IEEE 29.10.2023
• Subjects: Analog-digital Federated Learning; delay-aware federated learning; device scheduling; Federated learning; Optimal scheduling; over-the-air computation; Performance evaluation; Personal digital devices; Processor scheduling; Simulation; Wireless networks
• ISSN: 2576-2303
• DOI: 10.1109/IEEECONF59524.2023.10477031

Over-the-air (OTA) computation has recently emerged as a communication-efficient Federated Learning (FL) paradigm to train machine learning models over wireless networks. However, its performance is limited by the device with the worst SNR, resulting in fast yet noisy updates. On the other hand, allocating orthogonal resource blocks (RB) to individual devices via digital channels mitigates the noise problem, at the cost of increased communication latency. In this paper, we address this discrepancy and present ADFL, a novel Analog-Digital FL scheme: in each round, the parameter server (PS) schedules each device to either upload its gradient via the analog OTA scheme or transmit its quantized gradient over an orthogonal RB using the "digital" scheme. Focusing on a single FL round, we cast the optimal scheduling problem as the minimization of the mean squared error (MSE) on the estimated global gradient at the PS, subject to a delay constraint, yielding the optimal device scheduling configuration and quantization bits for the digital devices. Our simulation results show that ADFL, by scheduling most of the devices in OTA scheme while also occasionally employing the digital scheme for a few devices, consistently outperforms OTA-only and digital-only schemes, in both i.i.d. and non-i.i.d. settings.