Wei Jiang
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
Wei Jiang has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
Wu Luo
State Key Laboratory of Advanced Optical Communication Systems and Networks, School of Electronics, Peking University, Beijing, China
8 shared publications- Guangxu Zhu
Shenzhen Research Institute of Big Data
4 shared publications - Dingzhu Wen
ShanghaiTech University
2 shared publications Luxi Lu
2 shared publications- Peixi Liu
Shenzhen Research Institute of Big Data, Shenzhen, China
2 shared publications - Shuguang Cui
The Chinese University of Hong Kong
2 shared publications
Latest Publications
- 12 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (12) , 19767-19781
Sensing–Communication–Computation Integration for Federated Edge Learning With Controllable Model Dropout
FEderated Edge Learning (FEEL) is an advanced paradigm in edge artificial intelligence, enabling privacy-preserving collaborative model training through periodic communication between edge devices and a central server. FEEL involves three key processes: sensing, computation, and communication for data acquisition, processing, and exchange, respectively. Due to limited system resources, optimizing each process individually may lead to suboptimal learning performance. This challenge has sparked research into Integrated Sensing-Computation-Communication (ISCC) design for enhanced FEEL. While previous work has optimized general learning parameters such as batch size and computing frequency, there is a lack of customized designs considering the neural network architecture as an optimizable variable in ISCC for FEEL. To close this gap, we introduce a novel design where each device generates a sub-model through controllable weight dropout, adding flexibility by directly manipulating the learning process and reducing computation and communication overhead. To guide ISCC resource allocation in this new setting, we present a comprehensive convergence analysis, revealing the tight coupling of sensing, computation, and communication across devices and their impact on FEEL convergence. Building on these theoretical insights, we formulate an ISCC problem aiming to maximize the FEEL convergence rate through joint optimization of variables such as batch size, sensing power, dropout rate, and communication power. This non-convex problem is decomposed into two sub-problems via alternating optimization: one controls batch size using a sorting algorithm, while the other focuses on ISCC device parameters, transformable into a convex problem solved by successive convex approximation. Extensive experiments using human motion recognition datasets demonstrate the superiority of the proposed design over baseline schemes.
- 12 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (12) , 19767-19781
Sensing–Communication–Computation Integration for Federated Edge Learning With Controllable Model Dropout
FEderated Edge Learning (FEEL) is an advanced paradigm in edge artificial intelligence, enabling privacy-preserving collaborative model training through periodic communication between edge devices and a central server. FEEL involves three key processes: sensing, computation, and communication for data acquisition, processing, and exchange, respectively. Due to limited system resources, optimizing each process individually may lead to suboptimal learning performance. This challenge has sparked research into Integrated Sensing-Computation-Communication (ISCC) design for enhanced FEEL. While previous work has optimized general learning parameters such as batch size and computing frequency, there is a lack of customized designs considering the neural network architecture as an optimizable variable in ISCC for FEEL. To close this gap, we introduce a novel design where each device generates a sub-model through controllable weight dropout, adding flexibility by directly manipulating the learning process and reducing computation and communication overhead. To guide ISCC resource allocation in this new setting, we present a comprehensive convergence analysis, revealing the tight coupling of sensing, computation, and communication across devices and their impact on FEEL convergence. Building on these theoretical insights, we formulate an ISCC problem aiming to maximize the FEEL convergence rate through joint optimization of variables such as batch size, sensing power, dropout rate, and communication power. This non-convex problem is decomposed into two sub-problems via alternating optimization: one controls batch size using a sorting algorithm, while the other focuses on ISCC device parameters, transformable into a convex problem solved by successive convex approximation. Extensive experiments using human motion recognition datasets demonstrate the superiority of the proposed design over baseline schemes.
- 4 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (11) , 17818-17823
Task-Oriented Over-the-Air Computation for Edge-Device Co-Inference With Balanced Classification Accuracy
Edge-device co-inference, which concerns the cooperation between edge devices and an edge server for completing inference tasks over wireless networks, has been a promising technique for enabling various kinds of intelligent services at the network edge, e.g., auto-driving. In this paradigm, the concerned design objective of the network shifts from the traditional communication throughput to the effective and efficient execution of the inference task underpinned by the network, measured by, e.g., the inference accuracy and latency. In this paper, a task-oriented over-the-air computation scheme is proposed for a multi-device artificial intelligence system. Particularly, a novel tractable inference accuracy metric is proposed for classification tasks, which is called minimum pair-wise discriminant gain. Unlike prior work measuring the average of all class pairs in feature space, it measures the minimum distance of all class pairs. By maximizing the minimum pair-wise discriminant gain instead of its average counterpart, any pair of classes can be better separated in the feature space, and thus leading to a balanced and improved inference accuracy for all classes. Besides, this paper jointly optimizes the minimum discriminant gain of all feature elements instead of separately maximizing that of each element in the existing designs. As a result, the transmit power can be adaptively allocated to the feature elements according to their different contributions to the inference accuracy, opening an extra degree of freedom to improve inference performance. Extensive experiments are conducted using a concrete use case of human motion recognition to verify the superiority of the proposed design over the benchmarking scheme.
- 4 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (11) , 17818-17823
Task-Oriented Over-the-Air Computation for Edge-Device Co-Inference With Balanced Classification Accuracy
Edge-device co-inference, which concerns the cooperation between edge devices and an edge server for completing inference tasks over wireless networks, has been a promising technique for enabling various kinds of intelligent services at the network edge, e.g., auto-driving. In this paradigm, the concerned design objective of the network shifts from the traditional communication throughput to the effective and efficient execution of the inference task underpinned by the network, measured by, e.g., the inference accuracy and latency. In this paper, a task-oriented over-the-air computation scheme is proposed for a multi-device artificial intelligence system. Particularly, a novel tractable inference accuracy metric is proposed for classification tasks, which is called minimum pair-wise discriminant gain. Unlike prior work measuring the average of all class pairs in feature space, it measures the minimum distance of all class pairs. By maximizing the minimum pair-wise discriminant gain instead of its average counterpart, any pair of classes can be better separated in the feature space, and thus leading to a balanced and improved inference accuracy for all classes. Besides, this paper jointly optimizes the minimum discriminant gain of all feature elements instead of separately maximizing that of each element in the existing designs. As a result, the transmit power can be adaptively allocated to the feature elements according to their different contributions to the inference accuracy, opening an extra degree of freedom to improve inference performance. Extensive experiments are conducted using a concrete use case of human motion recognition to verify the superiority of the proposed design over the benchmarking scheme.
- 5 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 17 (1) , 158-172
Toward Ambient Intelligence: Federated Edge Learning With Task-Oriented Sensing, Computation, and Communication Integration
With the breakthroughs in deep learning and contactless sensors, the recent years have witnessed a rise of ambient intelligence applications and services, spanning from healthcare delivery to intelligent home. Federated edge learning (FEEL), as a privacy-enhancing paradigm of collaborative learning at the network edge, is expected to be the core engine to achieve ambient intelligence. Sensing, computation, and communication (SC $^{2}$ ) are highly coupled processes in FEEL and need to be jointly designed in a task-oriented manner to achieve the best FEEL performance under stringent resource constraints at edge devices. However, this remains an open problem as there is a lack of theoretical understanding on how the SC $^{2}$ resources jointly affect the FEEL performance. In this paper, we address the problem of joint SC $^{2}$ resource allocation for FEEL via a concrete case study of human motion recognition based on wireless sensing in ambient intelligence. First, by analyzing the wireless sensing process in human motion recognition, we find that there exists a thresholding value for the sensing transmit power, exceeding which yields sensing data samples with approximately the same satisfactory quality. Then, the joint SC $^{2}$ resource allocation problem is cast to maximize the convergence speed of FEEL, under the constraints on training time, energy supply, and sensing quality of each edge device. Solving this problem entails solving two subproblems in order: the first one reduces to determine the joint sensing and communication resource allocation that maximizes the total number of samples that can be sensed during the entire training process; the second one concerns the partition of the attained total number of sensed samples over all the communication rounds to determine the batch size at each round for convergence speed maximization. The first subproblem on joint sensing and communication resource allocation is converted to a single-variable optimization problem by exploiting the derived relation between different control variables (resources), which thus allows an efficient solution via one-dimensional grid search. For the second subproblem, it is found that the number of samples to be sensed (or batch size) at each round is a decreasing function of the loss function value attained at the round. Based on this relationship, the approximate optimal batch size at each communication round is derived in closed-form as a function of the round index. Finally, extensive simulation results are provided to validate the superiority of the proposed joint SC $^{2}$ resource allocation scheme over baseline schemes in terms of FEEL performance.
- 5 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 17 (1) , 158-172
Toward Ambient Intelligence: Federated Edge Learning With Task-Oriented Sensing, Computation, and Communication Integration
With the breakthroughs in deep learning and contactless sensors, the recent years have witnessed a rise of ambient intelligence applications and services, spanning from healthcare delivery to intelligent home. Federated edge learning (FEEL), as a privacy-enhancing paradigm of collaborative learning at the network edge, is expected to be the core engine to achieve ambient intelligence. Sensing, computation, and communication (SC $^{2}$ ) are highly coupled processes in FEEL and need to be jointly designed in a task-oriented manner to achieve the best FEEL performance under stringent resource constraints at edge devices. However, this remains an open problem as there is a lack of theoretical understanding on how the SC $^{2}$ resources jointly affect the FEEL performance. In this paper, we address the problem of joint SC $^{2}$ resource allocation for FEEL via a concrete case study of human motion recognition based on wireless sensing in ambient intelligence. First, by analyzing the wireless sensing process in human motion recognition, we find that there exists a thresholding value for the sensing transmit power, exceeding which yields sensing data samples with approximately the same satisfactory quality. Then, the joint SC $^{2}$ resource allocation problem is cast to maximize the convergence speed of FEEL, under the constraints on training time, energy supply, and sensing quality of each edge device. Solving this problem entails solving two subproblems in order: the first one reduces to determine the joint sensing and communication resource allocation that maximizes the total number of samples that can be sensed during the entire training process; the second one concerns the partition of the attained total number of sensed samples over all the communication rounds to determine the batch size at each round for convergence speed maximization. The first subproblem on joint sensing and communication resource allocation is converted to a single-variable optimization problem by exploiting the derived relation between different control variables (resources), which thus allows an efficient solution via one-dimensional grid search. For the second subproblem, it is found that the number of samples to be sensed (or batch size) at each round is a decreasing function of the loss function value attained at the round. Based on this relationship, the approximate optimal batch size at each communication round is derived in closed-form as a function of the round index. Finally, extensive simulation results are provided to validate the superiority of the proposed joint SC $^{2}$ resource allocation scheme over baseline schemes in terms of FEEL performance.
- 9 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 26 (9) , 2091-2095
Vertical Federated Edge Learning With Distributed Integrated Sensing and Communication
This letter studies a vertical federated edge learning (FEEL) system for collaborative objects/human motion recognition by exploiting the distributed integrated sensing and communication (ISAC). In this system, distributed edge devices first send wireless signals to sense targeted objects/human, and then exchange intermediate computed vectors (instead of raw sensing data) for collaborative recognition while preserving data privacy. To boost the spectrum and hardware utilization efficiency for FEEL, we exploit ISAC for both target sensing and data exchange, by employing dedicated frequency-modulated continuous-wave (FMCW) signals at each edge device. Under this setup, we propose a vertical FEEL scheme for realizing the recognition based on the collected multi-view wireless sensing data. In this scheme, each edge device owns an individual local L-model to transform its sensing data into an intermediate vector with relatively low dimensions, which is then transmitted to a coordinating edge device for final output via a common downstream S-model. By considering a human motion recognition task, experimental results show that our vertical FEEL based approach achieves recognition accuracy up to 98% with an improvement up to 8% compared to the benchmarks, including on-device training and horizontal FEEL.
- 9 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 26 (9) , 2091-2095
Vertical Federated Edge Learning With Distributed Integrated Sensing and Communication
This letter studies a vertical federated edge learning (FEEL) system for collaborative objects/human motion recognition by exploiting the distributed integrated sensing and communication (ISAC). In this system, distributed edge devices first send wireless signals to sense targeted objects/human, and then exchange intermediate computed vectors (instead of raw sensing data) for collaborative recognition while preserving data privacy. To boost the spectrum and hardware utilization efficiency for FEEL, we exploit ISAC for both target sensing and data exchange, by employing dedicated frequency-modulated continuous-wave (FMCW) signals at each edge device. Under this setup, we propose a vertical FEEL scheme for realizing the recognition based on the collected multi-view wireless sensing data. In this scheme, each edge device owns an individual local L-model to transform its sensing data into an intermediate vector with relatively low dimensions, which is then transmitted to a coordinating edge device for final output via a common downstream S-model. By considering a human motion recognition task, experimental results show that our vertical FEEL based approach achieves recognition accuracy up to 98% with an improvement up to 8% compared to the benchmarks, including on-device training and horizontal FEEL.
- Open Access
- 10 May 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 4, 2429-2438
Energy Efficient User Association for Cloud Radio Access Networks
Cloud radio access network (C-RAN) and massive multiple-input multiple-output (MIMO) are recognized as two key technologies for the fifth-generation mobile networks. In this paper, we consider the energy efficiency-based user association problem in massive MIMO empowered C-RAN, where multiple antennae are clustered at each remote radio head (RRH). We first obtain the deterministic equivalent expression of the energy efficiency, and then propose three user association algorithms, named nearest-based user association (NBUA), single-candidate RRH user association (SCRUA), and multi-candidate RRHs user association (MCRUA), respectively. In NBUA and SCRUA, each user is associated with only one RRH, and in MCRUA, multiple RRHs can serve the same user. In our algorithms, the impact of the power consumption of fronthaul links and antennas is considered by allowing inefficient RRHs to be turned into sleep mode. We provide the numerical comparisons of the proposed algorithms and a state-of-the-art baseline, which associates each user with the nearest RRH. The results show that our proposed algorithms achieve higher energy efficiency than the baseline algorithm. The proposed MCRUA algorithm achieves a good balance between spectral and energy efficiency, and the performance gain is more significant when the number of users is large.
- 10 May 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 4, 2429-2438
Open AccessEnergy Efficient User Association for Cloud Radio Access Networks
Cloud radio access network (C-RAN) and massive multiple-input multiple-output (MIMO) are recognized as two key technologies for the fifth-generation mobile networks. In this paper, we consider the energy efficiency-based user association problem in massive MIMO empowered C-RAN, where multiple antennae are clustered at each remote radio head (RRH). We first obtain the deterministic equivalent expression of the energy efficiency, and then propose three user association algorithms, named nearest-based user association (NBUA), single-candidate RRH user association (SCRUA), and multi-candidate RRHs user association (MCRUA), respectively. In NBUA and SCRUA, each user is associated with only one RRH, and in MCRUA, multiple RRHs can serve the same user. In our algorithms, the impact of the power consumption of fronthaul links and antennas is considered by allowing inefficient RRHs to be turned into sleep mode. We provide the numerical comparisons of the proposed algorithms and a state-of-the-art baseline, which associates each user with the nearest RRH. The results show that our proposed algorithms achieve higher energy efficiency than the baseline algorithm. The proposed MCRUA algorithm achieves a good balance between spectral and energy efficiency, and the performance gain is more significant when the number of users is large.
- Open Access
- 12 March 2015
- Published by Wiley in International Journal of Antennas and Propagation
- Vol. 2015, 1-11
Outage-Constrained Beamforming for Two-Tier Massive MIMO Downlink with Pilot Reuse
Massive multiple-input multiple-output (MIMO) systems and small cell networks are both regarded as promising candidates to meet the exponential growth of mobile data traffic for the next generation (5G) wireless communications. Hence, a new kind of multitier networks which combine massive MIMO macro cells with a secondary tier of small cells is proposed to resolve the contradiction of large network coverage and high data rate. In such multitier networks, it is inevitable to allocate nonorthogonal uplink pilot sequences to user equipment (UE) due to the large number of users. We propose a pilot reuse scheme by exploiting the unique architecture of this networks and analyse the special mixed channel state information (CSI) yielded by the pilot reuse scheme. Based on the mixed CSI, we formulate a downlink transmit beamforming problem of minimizing the total power consumption while satisfying the quality of service (QoS) requirements with outage constraints. After decomposing the original problem into simpler subproblems, we provide an efficient algorithm to combine these subproblems and solve them iteratively for generating the beamforming vectors. Monte Carlo simulations show that the average power consumption of the proposed pilot reuse scheme and its associated beamforming algorithm is close to that of the perfect CSI case.
- 12 March 2015
- Published by Wiley in International Journal of Antennas and Propagation
- Vol. 2015, 1-11
Open AccessOutage-Constrained Beamforming for Two-Tier Massive MIMO Downlink with Pilot Reuse
Massive multiple-input multiple-output (MIMO) systems and small cell networks are both regarded as promising candidates to meet the exponential growth of mobile data traffic for the next generation (5G) wireless communications. Hence, a new kind of multitier networks which combine massive MIMO macro cells with a secondary tier of small cells is proposed to resolve the contradiction of large network coverage and high data rate. In such multitier networks, it is inevitable to allocate nonorthogonal uplink pilot sequences to user equipment (UE) due to the large number of users. We propose a pilot reuse scheme by exploiting the unique architecture of this networks and analyse the special mixed channel state information (CSI) yielded by the pilot reuse scheme. Based on the mixed CSI, we formulate a downlink transmit beamforming problem of minimizing the total power consumption while satisfying the quality of service (QoS) requirements with outage constraints. After decomposing the original problem into simpler subproblems, we provide an efficient algorithm to combine these subproblems and solve them iteratively for generating the beamforming vectors. Monte Carlo simulations show that the average power consumption of the proposed pilot reuse scheme and its associated beamforming algorithm is close to that of the perfect CSI case.
- 1 March 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15253511,p. 1332-1337
Uplink traffic cellular-first access scheme in cellular/WLAN integrated networks
In cellular/WLAN integrated networks, WLAN APs are usually deployed to offload the heavy traffic of cellular networks. Due to the inherent asymmetry of downlink and uplink in WLAN, competitions increase rapidly along with uplink traffic being offloaded to WLAN, which degrades system performance significantly. In this paper, we propose a new access scheme, i.e. uplink traffic cellular-first access (UTCFA) scheme. By offloading uplink traffic within WLAN coverage to contention-free cellular networks as much as possible, UTCFA scheme improves WLAN channel utilization significantly. We derive the throughput produced by UTCFA by theoretical analysis and perform extensive simulations to validate these theoretical results. Particularly, we find that the well-known WLAN-first access scheme is a special case of the proposed scheme. The simulation results also show that UTCFA can significantly improve the system performance and provide better support for quality of service guaranteed services.
- 1 March 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15253511,p. 1332-1337
Uplink traffic cellular-first access scheme in cellular/WLAN integrated networks
In cellular/WLAN integrated networks, WLAN APs are usually deployed to offload the heavy traffic of cellular networks. Due to the inherent asymmetry of downlink and uplink in WLAN, competitions increase rapidly along with uplink traffic being offloaded to WLAN, which degrades system performance significantly. In this paper, we propose a new access scheme, i.e. uplink traffic cellular-first access (UTCFA) scheme. By offloading uplink traffic within WLAN coverage to contention-free cellular networks as much as possible, UTCFA scheme improves WLAN channel utilization significantly. We derive the throughput produced by UTCFA by theoretical analysis and perform extensive simulations to validate these theoretical results. Particularly, we find that the well-known WLAN-first access scheme is a special case of the proposed scheme. The simulation results also show that UTCFA can significantly improve the system performance and provide better support for quality of service guaranteed services.
- 20 January 2013
- Published by China Science Publishing & Media Ltd. in Journal of Electronics & Information Technology
- Vol. 35 (1) , 166-171
Joint Estimation of Doppler Frequency Shift and Doppler Frequency Rate Based on Interpolation
- 20 January 2013
- Published by China Science Publishing & Media Ltd. in Journal of Electronics & Information Technology
- Vol. 35 (1) , 166-171
Joint Estimation of Doppler Frequency Shift and Doppler Frequency Rate Based on Interpolation
- 20 October 2012
- Published by China Science Publishing & Media Ltd. in Journal of Electronics & Information Technology
- Vol. 34 (10) , 2326-2330
A Maximum Likelihood Estimation of Subchip Multipath Parameters
- 20 October 2012
- Published by China Science Publishing & Media Ltd. in Journal of Electronics & Information Technology
- Vol. 34 (10) , 2326-2330
A Maximum Likelihood Estimation of Subchip Multipath Parameters
- 1 January 2011
- Published by ASME International
- p. 13-18
Iterative User Selection Scheme for MIMO Broadcast Channels in Circuit Data Scenarios
- 1 January 2011
- Published by ASME International
- p. 13-18
Iterative User Selection Scheme for MIMO Broadcast Channels in Circuit Data Scenarios