no code implementations • 27 Oct 2023 • Wenzhi Fang, Dong-Jun Han, Christopher G. Brinton
Hierarchical federated learning (HFL) has demonstrated promising scalability advantages over the traditional "star-topology" architecture-based federated learning (FL).
1 code implementation • 24 Jan 2022 • Wenzhi Fang, Ziyi Yu, Yuning Jiang, Yuanming Shi, Colin N. Jones, Yong Zhou
Under non-convex settings, we derive the convergence performance of the FedZO algorithm on non-independent and identically distributed data and characterize the impact of the numbers of local iterates and participating edge devices on the convergence.
no code implementations • 11 May 2021 • Wenzhi Fang, Yinan Zou, Hongbin Zhu, Yuanming Shi, Yong Zhou
In this paper, we consider fast wireless data aggregation via over-the-air computation (AirComp) in Internet of Things (IoT) networks, where an access point (AP) with multiple antennas aim to recover the arithmetic mean of sensory data from multiple IoT devices.
no code implementations • 11 May 2021 • Wenzhi Fang, Yuning Jiang, Yuanming Shi, Yong Zhou, Wei Chen, Khaled B. Letaief
Over-the-air computation (AirComp) is a disruptive technique for fast wireless data aggregation in Internet of Things (IoT) networks via exploiting the waveform superposition property of multiple-access channels.