Zhiyuan Zhai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zhiyuan Zhai has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Xiaojun Yuan
University of Electronic Science and Technology of China
7 shared publications - Xin Wang
Fudan University
7 shared publications - Geoffrey Ye Li
Imperial College London
2 shared publications - Huiyuan Yang
National Key Laboratory on Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication - Jie Wu
Cloud Computing Research Institute, China Telecom
1 shared publication - Manos M. Tentzeris
Georgia Institute of Technology
1 shared publication
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (11) , 14744-14758
Event-Triggered Gossip for Distributed Learning
While distributed learning offers a new learning paradigm for distributed network with no central coordination, it is constrained by communication bottleneck between nodes. We develop a new event-triggered gossip framework for distributed learning to reduce inter-node communication overhead. The framework introduces an adaptive communication control mechanism that enables each node to autonomously decide in a fully decentralized fashion when to exchange model information with its neighbors based on local model deviations. We analyze the ergodic convergence of the proposed framework under nonconvex objectives and interpret the convergence guarantees under different triggering conditions. Simulation results show that the proposed framework achieves substantially lower communication overhead than the state-of-the-art distributed learning methods, reducing cumulative point-to-point transmissions by 71.61% with only a marginal performance loss, compared with the conventional full-communication baseline.
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (11) , 14744-14758
Event-Triggered Gossip for Distributed Learning
While distributed learning offers a new learning paradigm for distributed network with no central coordination, it is constrained by communication bottleneck between nodes. We develop a new event-triggered gossip framework for distributed learning to reduce inter-node communication overhead. The framework introduces an adaptive communication control mechanism that enables each node to autonomously decide in a fully decentralized fashion when to exchange model information with its neighbors based on local model deviations. We analyze the ergodic convergence of the proposed framework under nonconvex objectives and interpret the convergence guarantees under different triggering conditions. Simulation results show that the proposed framework achieves substantially lower communication overhead than the state-of-the-art distributed learning methods, reducing cumulative point-to-point transmissions by 71.61% with only a marginal performance loss, compared with the conventional full-communication baseline.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (10) , 25157-25169
Trajectory Design for UAV-Assisted Logistics Collection in Low-Altitude Economy
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (10) , 25157-25169
Trajectory Design for UAV-Assisted Logistics Collection in Low-Altitude Economy
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (7) , 10788-10799
Spectral-Convergent Decentralized Machine Learning: Theory and Application in Space Networks
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (7) , 10788-10799
Spectral-Convergent Decentralized Machine Learning: Theory and Application in Space Networks
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 3899-3910
Decentralized Federated Learning With Distributed Aggregation Weight Optimization
Decentralized federated learning (DFL) is an emerging paradigm to enable edge devices collaboratively training a learning model using a device-to-device (D2D) communication manner without the coordination of a parameter server (PS). Aggregation weights, also known as mixing weights, are crucial in DFL process, and impact the learning efficiency and accuracy. Conventional design relies on a so-called central entity to collect all local information and conduct system optimization to obtain appropriate weights. In this paper, we develop a distributed aggregation weight optimization algorithm to align with the decentralized nature of DFL. We analyze convergence by quantitatively capturing the impact of the aggregation weights over decentralized communication networks. Based on the analysis, we then formulate a learning performance optimization problem by designing the aggregation weights to minimize the derived convergence bound. The optimization problem is further transformed as an eigenvalue optimization problem and solved by our proposed subgradient-based algorithm in a distributed fashion. In our algorithm, edge devices only need local information to obtain the optimal aggregation weights through local (D2D) communications, just like the learning itself. Therefore, the optimization, communication, and learning process can be all conducted in a distributed fashion, which leads to a genuinely distributed DFL system. Numerical results demonstrate the superiority of the proposed algorithm in practical DFL deployment.
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 3899-3910
Decentralized Federated Learning With Distributed Aggregation Weight Optimization
Decentralized federated learning (DFL) is an emerging paradigm to enable edge devices collaboratively training a learning model using a device-to-device (D2D) communication manner without the coordination of a parameter server (PS). Aggregation weights, also known as mixing weights, are crucial in DFL process, and impact the learning efficiency and accuracy. Conventional design relies on a so-called central entity to collect all local information and conduct system optimization to obtain appropriate weights. In this paper, we develop a distributed aggregation weight optimization algorithm to align with the decentralized nature of DFL. We analyze convergence by quantitatively capturing the impact of the aggregation weights over decentralized communication networks. Based on the analysis, we then formulate a learning performance optimization problem by designing the aggregation weights to minimize the derived convergence bound. The optimization problem is further transformed as an eigenvalue optimization problem and solved by our proposed subgradient-based algorithm in a distributed fashion. In our algorithm, edge devices only need local information to obtain the optimal aggregation weights through local (D2D) communications, just like the learning itself. Therefore, the optimization, communication, and learning process can be all conducted in a distributed fashion, which leads to a genuinely distributed DFL system. Numerical results demonstrate the superiority of the proposed algorithm in practical DFL deployment.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 2383-2396
Distributed Weight Matrix Optimization for Consensus Problems Under Unreliable Communications
Consensus in ad hoc networks is fundamental for coordinating tasks such as cooperative sensing, learning, and data fusion. Till now, designing algorithm to tackle consensus problem primarily faces two critical challenges: The first is the imperfection of communication links between nodes, and the second is the unavailability of central node collecting network information. To address these challenges, this paper investigates the consensus problem under unreliable communications and develops a distributed weight matrix optimization approach to improve consensus performance. Specifically, we quantitatively analyze the impact of mixing weights on consensus error over unreliable communications. Guided by this analysis, we formulate a stochastic eigenvalue optimization problem to optimize the weight matrix for maximizing consensus performance. Typically, solving such problem in a distributed manner is impractical. However, by leveraging the inherent structure of the problem, a novel distributed projected subgradient-based algorithm is developed to obtain the optimal weight matrix. Simulation results validate the effectiveness of the proposed approach under different network configurations. The proposed method also shows robust performance when benchmarked against existing schemes, making it well-suited for deployment in large-scale distributed networks.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 2383-2396
Distributed Weight Matrix Optimization for Consensus Problems Under Unreliable Communications
Consensus in ad hoc networks is fundamental for coordinating tasks such as cooperative sensing, learning, and data fusion. Till now, designing algorithm to tackle consensus problem primarily faces two critical challenges: The first is the imperfection of communication links between nodes, and the second is the unavailability of central node collecting network information. To address these challenges, this paper investigates the consensus problem under unreliable communications and develops a distributed weight matrix optimization approach to improve consensus performance. Specifically, we quantitatively analyze the impact of mixing weights on consensus error over unreliable communications. Guided by this analysis, we formulate a stochastic eigenvalue optimization problem to optimize the weight matrix for maximizing consensus performance. Typically, solving such problem in a distributed manner is impractical. However, by leveraging the inherent structure of the problem, a novel distributed projected subgradient-based algorithm is developed to obtain the optimal weight matrix. Simulation results validate the effectiveness of the proposed approach under different network configurations. The proposed method also shows robust performance when benchmarked against existing schemes, making it well-suited for deployment in large-scale distributed networks.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (3) , 2358-2372
UAV-Enabled Asynchronous Federated Learning
To exploit unprecedented data generation in mobile edge networks, federated learning (FL) has emerged as a promising alternative to the conventional centralized machine learning (ML). By collectively training a unified learning model on edge devices, FL bypasses the need of direct data transmission, thereby addressing problems such as latency issues and privacy concerns inherent in centralized ML. However, in practical deployment FL suffers from low learning efficiency due to the involved straggler issue and huge uplink overhead. In this paper, we develop a UAV-enabled over-the-air asynchronous FL (UAV-AFL) framework to address this problem. This framework significantly enhance the learning efficiency by supporting the UAV as the parameter server (UAV-PS) in collecting data over-the-air and updating model continuously. We conduct a convergence analysis to quantitatively capture the impact of model asynchrony, device selection and communication errors on the UAV-AFL learning efficiency. Based on this analysis, a unified communication-learning problem is formulated to maximize asymptotical learning accuracy by optimizing the UAV-PS trajectory, device selection and over-the-air transceiver design. Simulation results reveal valuable insights for the system design and demonstrate that the proposed UAV-AFL scheme achieves substantially improvement in learning efficiency compared with the state-of-the-art approaches.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (3) , 2358-2372
UAV-Enabled Asynchronous Federated Learning
To exploit unprecedented data generation in mobile edge networks, federated learning (FL) has emerged as a promising alternative to the conventional centralized machine learning (ML). By collectively training a unified learning model on edge devices, FL bypasses the need of direct data transmission, thereby addressing problems such as latency issues and privacy concerns inherent in centralized ML. However, in practical deployment FL suffers from low learning efficiency due to the involved straggler issue and huge uplink overhead. In this paper, we develop a UAV-enabled over-the-air asynchronous FL (UAV-AFL) framework to address this problem. This framework significantly enhance the learning efficiency by supporting the UAV as the parameter server (UAV-PS) in collecting data over-the-air and updating model continuously. We conduct a convergence analysis to quantitatively capture the impact of model asynchrony, device selection and communication errors on the UAV-AFL learning efficiency. Based on this analysis, a unified communication-learning problem is formulated to maximize asymptotical learning accuracy by optimizing the UAV-PS trajectory, device selection and over-the-air transceiver design. Simulation results reveal valuable insights for the system design and demonstrate that the proposed UAV-AFL scheme achieves substantially improvement in learning efficiency compared with the state-of-the-art approaches.
- 19 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (9) , 11847-11862
Decentralized Federated Learning via MIMO Over-the-Air Computation: Consensus Analysis and Performance Optimization
Decentralized federated learning (DFL), inherited from distributed optimization, is an emerging paradigm to leverage the explosively growing data from wireless devices in a fully distributed manner. With the cooperation of edge devices, DFL enables joint training of machine learning model in a device to device (D2D) communication fashion without the coordination of a parameter server. However, the deployment of wireless DFL is facing some pivotal challenges. Communication is a critical bottleneck due to the required extensive message exchanges between neighbor devices to share the learned model. Besides, model consensus becomes increasingly difficult as the number of devices grows because there is no available central server for coordination. To overcome these difficulties, this paper proposes the use of over-the-air computation (Aircomp) to improve communication efficiency by exploiting the superposition property of analog waveforms in multi-access channels, and introduce the mixing matrix mechanism to promote consensus using the spectral property of symmetric doubly stochastic matrix. Specifically, we develop a novel multiple-input multiple-output (MIMO) over-the-air DFL (OA-DFL) framework to study over-the-air DFL problem over MIMO multiple access channels. We conduct a general convergence analysis to quantitatively capture the impact of aggregation weights and communication error on the MIMO OA-DFL performance in ad hoc D2D networks. The result shows that the communication error together with the spectral gap of the mixing matrix has a significant impact on the learning performance. Based on this, a joint communication-learning optimization problem is formulated to optimize the transceiver beamformers and the mixing matrix. Extensive numerical experiments are performed to reveal the characteristics of different topologies and demonstrate the substantial learning performance enhancement of our proposed algorithm.
- 19 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (9) , 11847-11862
Decentralized Federated Learning via MIMO Over-the-Air Computation: Consensus Analysis and Performance Optimization
Decentralized federated learning (DFL), inherited from distributed optimization, is an emerging paradigm to leverage the explosively growing data from wireless devices in a fully distributed manner. With the cooperation of edge devices, DFL enables joint training of machine learning model in a device to device (D2D) communication fashion without the coordination of a parameter server. However, the deployment of wireless DFL is facing some pivotal challenges. Communication is a critical bottleneck due to the required extensive message exchanges between neighbor devices to share the learned model. Besides, model consensus becomes increasingly difficult as the number of devices grows because there is no available central server for coordination. To overcome these difficulties, this paper proposes the use of over-the-air computation (Aircomp) to improve communication efficiency by exploiting the superposition property of analog waveforms in multi-access channels, and introduce the mixing matrix mechanism to promote consensus using the spectral property of symmetric doubly stochastic matrix. Specifically, we develop a novel multiple-input multiple-output (MIMO) over-the-air DFL (OA-DFL) framework to study over-the-air DFL problem over MIMO multiple access channels. We conduct a general convergence analysis to quantitatively capture the impact of aggregation weights and communication error on the MIMO OA-DFL performance in ad hoc D2D networks. The result shows that the communication error together with the spectral gap of the mixing matrix has a significant impact on the learning performance. Based on this, a joint communication-learning optimization problem is formulated to optimize the transceiver beamformers and the mixing matrix. Extensive numerical experiments are performed to reveal the characteristics of different topologies and demonstrate the substantial learning performance enhancement of our proposed algorithm.
- 1 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-3
A Frequency Tunable Wideband Circularly Polarized Antenna
A wideband frequency tunable circularly polarized (CP) crossed dipole antenna with a wide beamwidth is presented. The proposed antenna consists of two crossed dipoles, four screws, and a modified cavity. By replacing the screws, the proposed antenna can work in different frequency bands. The simulated results show the tunable impedance bandwidth for $\text{VSWR}\leqslant 2$ is 57% from 1.19 GHz to 2.14 GHz and the 3-dB axial ratio (AR) band is covered from 1.27 GHz to 1.92 GHz (41%). The 3-dB AR beamwidth and half power beamwidth are more than 120º at the operating frequencies. Thus, the designed antenna is a promising candidate for modern wireless communication system.- 1 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-3
A Frequency Tunable Wideband Circularly Polarized Antenna
A wideband frequency tunable circularly polarized (CP) crossed dipole antenna with a wide beamwidth is presented. The proposed antenna consists of two crossed dipoles, four screws, and a modified cavity. By replacing the screws, the proposed antenna can work in different frequency bands. The simulated results show the tunable impedance bandwidth for $\text{VSWR}\leqslant 2$ is 57% from 1.19 GHz to 2.14 GHz and the 3-dB axial ratio (AR) band is covered from 1.27 GHz to 1.92 GHz (41%). The 3-dB AR beamwidth and half power beamwidth are more than 120º at the operating frequencies. Thus, the designed antenna is a promising candidate for modern wireless communication system.