Zheshun Wu
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
Zheshun Wu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Jie Liu
Harbin Institute of Technology, Shenzhen, China
6 shared publications - Zenglin Xu
Shanghai Academy of AI for Science Shanghai China
5 shared publications - Dun Zeng
Department of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Junfan Li
School of Computer Science and Technology, State Key Laboratory of Smart Farm Technologies and System, Harbin Institute of Technology Shenzhen, Shenzhen, China
2 shared publications - Qifan Wang
Meta Platforms, Menlo Park, CA, USA
2 shared publications Xiaoping Wu
School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China
2 shared publications
Latest Publications
- Open Access
- 10 April 2027
- Published by Association for Computing Machinery (ACM)
- p. 889-905
SparseDVFS: Sparsity-aware DVFS for Energy-Efficient Edge Inference
- 10 April 2027
- Published by Association for Computing Machinery (ACM)
- p. 889-905
Open AccessSparseDVFS: Sparsity-aware DVFS for Energy-Efficient Edge Inference
- 18 February 2026
- Published by Elsevier in Neural Networks
- Vol. 199, 108733
Enhancing progressive ensemble learning via normalized extra-Gradient initialization
- 18 February 2026
- Published by Elsevier in Neural Networks
- Vol. 199, 108733
Enhancing progressive ensemble learning via normalized extra-Gradient initialization
- 4 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 1992-2007
Online Optimization for Learning to Communicate Over Time-Correlated Channels
Machine learning techniques have garnered great interest in designing communication systems owing to their capacity in tackling with channel uncertainty. To provide theoretical guarantees for learning-based communication systems, some recent works analyze generalization bounds for devised methods based on the assumption of Independently and Identically Distributed (I.I.D.) channels, a condition rarely met in practical scenarios. In this article, we drop the I.I.D. channel assumption and study an online optimization problem of learning to communicate over time-correlated channels. To address this issue, we further focus on two specific tasks: optimizing channel decoders for time-correlated fading channels and selecting optimal codebooks for time-correlated additive noise channels. For utilizing temporal dependence of considered channels to better learn communication systems, we develop two online optimization algorithms based on the optimistic online mirror descent framework. Furthermore, we provide theoretical guarantees for proposed algorithms via deriving sub-linear regret bound on the expected error probability of learned systems. Extensive simulation experiments have been conducted to validate that our presented approaches can leverage the channel correlation to achieve a lower average symbol error rate compared to baseline methods, consistent with our theoretical findings.
- 4 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 1992-2007
Online Optimization for Learning to Communicate Over Time-Correlated Channels
Machine learning techniques have garnered great interest in designing communication systems owing to their capacity in tackling with channel uncertainty. To provide theoretical guarantees for learning-based communication systems, some recent works analyze generalization bounds for devised methods based on the assumption of Independently and Identically Distributed (I.I.D.) channels, a condition rarely met in practical scenarios. In this article, we drop the I.I.D. channel assumption and study an online optimization problem of learning to communicate over time-correlated channels. To address this issue, we further focus on two specific tasks: optimizing channel decoders for time-correlated fading channels and selecting optimal codebooks for time-correlated additive noise channels. For utilizing temporal dependence of considered channels to better learn communication systems, we develop two online optimization algorithms based on the optimistic online mirror descent framework. Furthermore, we provide theoretical guarantees for proposed algorithms via deriving sub-linear regret bound on the expected error probability of learned systems. Extensive simulation experiments have been conducted to validate that our presented approaches can leverage the channel correlation to achieve a lower average symbol error rate compared to baseline methods, consistent with our theoretical findings.
- 27 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 14174-14188
Advocating for the Silent: Enhancing Federated Generalization for Nonparticipating Clients
Federated learning (FL) has surged in prominence due to its capability of collaborative model training without direct data sharing. However, the vast disparity in local data distributions among clients, often termed the nonindependent identically distributed (Non-IID) challenge, poses a significant hurdle to FL’s generalization efficacy. The scenario becomes even more complex when not all clients participate in the training process, a common occurrence due to unstable network connections or limited computational capacities. This can greatly complicate the assessment of the trained models’ generalization abilities. While a plethora of recent studies has centered on the generalization gap pertaining to unseen data from participating clients with diverse distributions, the distinction between the training distributions of participating clients and the testing distributions of nonparticipating ones has been largely overlooked. In response, our paper unveils an information-theoretic generalization framework for FL. Specifically, it quantifies generalization errors by evaluating the information entropy of local distributions and discerning discrepancies across these distributions. Inspired by our deduced generalization bounds, we introduce a weighted aggregation approach and a duo of client selection strategies. These innovations are designed to strengthen FL’s ability to generalize and thus ensure that trained models perform better on nonparticipating clients by incorporating a more diverse range of client data distributions. Our extensive empirical evaluations reaffirm the potency of our proposed methods, aligning seamlessly with our theoretical construct.
- 27 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (8) , 14174-14188
Advocating for the Silent: Enhancing Federated Generalization for Nonparticipating Clients
Federated learning (FL) has surged in prominence due to its capability of collaborative model training without direct data sharing. However, the vast disparity in local data distributions among clients, often termed the nonindependent identically distributed (Non-IID) challenge, poses a significant hurdle to FL’s generalization efficacy. The scenario becomes even more complex when not all clients participate in the training process, a common occurrence due to unstable network connections or limited computational capacities. This can greatly complicate the assessment of the trained models’ generalization abilities. While a plethora of recent studies has centered on the generalization gap pertaining to unseen data from participating clients with diverse distributions, the distinction between the training distributions of participating clients and the testing distributions of nonparticipating ones has been largely overlooked. In response, our paper unveils an information-theoretic generalization framework for FL. Specifically, it quantifies generalization errors by evaluating the information entropy of local distributions and discerning discrepancies across these distributions. Inspired by our deduced generalization bounds, we introduce a weighted aggregation approach and a duo of client selection strategies. These innovations are designed to strengthen FL’s ability to generalize and thus ensure that trained models perform better on nonparticipating clients by incorporating a more diverse range of client data distributions. Our extensive empirical evaluations reaffirm the potency of our proposed methods, aligning seamlessly with our theoretical construct.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (8) , 12201-12206
Topology Learning for Heterogeneous Decentralized Federated Learning Over Unreliable D2D Networks
With the proliferation of intelligent mobile devices in wireless device-to-device (D2D) networks, decentralized federated learning (DFL) has attracted significant interest. Compared to centralized federated learning (CFL), DFL mitigates the risk of central server failures due to communication bottlenecks. However, DFL faces several challenges, such as the severe heterogeneity of data distributions in diverse environments, and the transmission outages and package errors caused by the adoption of the User Datagram Protocol (UDP) in D2D networks. These challenges often degrade the convergence of training DFL models. To address these challenges, we conduct a thorough theoretical convergence analysis for DFL and derive a convergence bound. By defining a novel quantity named unreliable links-aware neighborhood discrepancy in this convergence bound, we formulate a tractable optimization objective, and develop a novel Topology Learning method considering the Representation Discrepancy and Unreliable Links in DFL, named ToLRDUL. Intensive experiments under both feature skew and label skew settings have validated the effectiveness of our proposed method, demonstrating improved convergence speed and test accuracy, consistent with our theoretical findings.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (8) , 12201-12206
Topology Learning for Heterogeneous Decentralized Federated Learning Over Unreliable D2D Networks
With the proliferation of intelligent mobile devices in wireless device-to-device (D2D) networks, decentralized federated learning (DFL) has attracted significant interest. Compared to centralized federated learning (CFL), DFL mitigates the risk of central server failures due to communication bottlenecks. However, DFL faces several challenges, such as the severe heterogeneity of data distributions in diverse environments, and the transmission outages and package errors caused by the adoption of the User Datagram Protocol (UDP) in D2D networks. These challenges often degrade the convergence of training DFL models. To address these challenges, we conduct a thorough theoretical convergence analysis for DFL and derive a convergence bound. By defining a novel quantity named unreliable links-aware neighborhood discrepancy in this convergence bound, we formulate a tractable optimization objective, and develop a novel Topology Learning method considering the Representation Discrepancy and Unreliable Links in DFL, named ToLRDUL. Intensive experiments under both feature skew and label skew settings have validated the effectiveness of our proposed method, demonstrating improved convergence speed and test accuracy, consistent with our theoretical findings.
- 26 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 691-695
Information-Theoretic Generalization Analysis for Topology-Aware Heterogeneous Federated Edge Learning Over Noisy Channels
With the rapid growth of edge intelligence, the deployment of federated learning (FL) over wireless networks has garnered increasing attention, which is called Federated Edge Learning (FEEL). In FEEL, both mobile devices transmitting model parameters over noisy channels and collecting data in diverse environments pose challenges to the generalization of trained models. Moreover, devices can engage in decentralized FL via Device-to-Device communication while the communication topology of connected devices also impacts the generalization of models. Most recent theoretical studies overlook the incorporation of all these effects into FEEL when developing generalization analyses and ignore designing algorithms to enhance the generalization of models based on their analysis. In contrast, our work presents an information-theoretic generalization analysis for topology-aware FEEL with data heterogeneity and noisy channels. Additionally, we propose a novel regularization method called Federated Global Mutual Information Reduction (FedGMIR) to enhance the performance of models based on our analysis. Numerical results validate our theoretical findings and provide evidence for the effectiveness of the proposed method.
- 26 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 691-695
Information-Theoretic Generalization Analysis for Topology-Aware Heterogeneous Federated Edge Learning Over Noisy Channels
With the rapid growth of edge intelligence, the deployment of federated learning (FL) over wireless networks has garnered increasing attention, which is called Federated Edge Learning (FEEL). In FEEL, both mobile devices transmitting model parameters over noisy channels and collecting data in diverse environments pose challenges to the generalization of trained models. Moreover, devices can engage in decentralized FL via Device-to-Device communication while the communication topology of connected devices also impacts the generalization of models. Most recent theoretical studies overlook the incorporation of all these effects into FEEL when developing generalization analyses and ignore designing algorithms to enhance the generalization of models based on their analysis. In contrast, our work presents an information-theoretic generalization analysis for topology-aware FEEL with data heterogeneity and noisy channels. Additionally, we propose a novel regularization method called Federated Global Mutual Information Reduction (FedGMIR) to enhance the performance of models based on our analysis. Numerical results validate our theoretical findings and provide evidence for the effectiveness of the proposed method.
- 27 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 20 (3) , 3359-3379
Joint Scheduling and Robust Aggregation for Federated Localization Over Unreliable Wireless D2D Networks
Deep learning-assisted indoor fingerprint localization based on frequent data collection is motivating renewed interest via crowdsourcing. Uploading raw training data may cause exposure of privacy in crowdsourcing. Federated Learning (FL) is thus introduced into indoor localization since its advantages in privacy protection. Nevertheless, most current FL-based indoor localization studies do not consider deploying systems in real wireless environments. Furthermore, transmission latency and outages caused by unreliable wireless networks are ignored. In addition, centralized FL-based indoor localization is adopted in most studies while decentralized FL-based indoor localization system is seldomly considered. In this paper, a decentralized Federated Learning (DFL)-based indoor localization system over wireless D2D networks is proposed for mitigating effects from single point of failure and communication bottleneck from centralized FL. Moreover, unreliable wireless links are further considered. To reduce the transmission latency, a greedy-based scheduling policy is devised to select DFL participants via jointly considering channel condition and scheduling fairness. For the possible transmission outages, a maximum distribution similarity-based successive model decoding aggregation algorithm is proposed to aggregate models more robustly and the corresponding theoretical analysis is provided. Experimental results based on real-world dataset collected by us show that proposed methods achieve better performance both in reducing latency and localization error than baseline schemes.
- 27 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 20 (3) , 3359-3379
Joint Scheduling and Robust Aggregation for Federated Localization Over Unreliable Wireless D2D Networks
Deep learning-assisted indoor fingerprint localization based on frequent data collection is motivating renewed interest via crowdsourcing. Uploading raw training data may cause exposure of privacy in crowdsourcing. Federated Learning (FL) is thus introduced into indoor localization since its advantages in privacy protection. Nevertheless, most current FL-based indoor localization studies do not consider deploying systems in real wireless environments. Furthermore, transmission latency and outages caused by unreliable wireless networks are ignored. In addition, centralized FL-based indoor localization is adopted in most studies while decentralized FL-based indoor localization system is seldomly considered. In this paper, a decentralized Federated Learning (DFL)-based indoor localization system over wireless D2D networks is proposed for mitigating effects from single point of failure and communication bottleneck from centralized FL. Moreover, unreliable wireless links are further considered. To reduce the transmission latency, a greedy-based scheduling policy is devised to select DFL participants via jointly considering channel condition and scheduling fairness. For the possible transmission outages, a maximum distribution similarity-based successive model decoding aggregation algorithm is proposed to aggregate models more robustly and the corresponding theoretical analysis is provided. Experimental results based on real-world dataset collected by us show that proposed methods achieve better performance both in reducing latency and localization error than baseline schemes.
- 5 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (11) , 10640-10654
Prediction Based Semi-Supervised Online Personalized Federated Learning for Indoor Localization
Fingerprint-based indoor localization has drawn increasing attention with the development of deep learning. Nevertheless, it faces challenges from frequent data collection and the corresponding exposure of privacy. Federated Learning (FL) is introduced into indoor localization recently for overcoming these challenges. However, most of the current FL-based indoor localization studies only focus on the static data distributions and ignore the fact that users have their preferred localization requirements. In this paper, two typical indoor localization scenarios are considered. Clients with various localization demands and data distributions collect online unlabeled data in Scenario I. For Scenario II, only one requesting user (RU) with high mobility applies for the localization service. A Prediction based Semi-supervised Online Personalized Federated Learning (PSO-PFL) is proposed for addressing these problems in the two scenarios. Experiments are conducted based on two real-world datasets. The experiment results show that PSO-PFL achieves higher personalization accuracy than centralized training and Federated Averaging, and utilizes unlabeled data efficiently. The strategy of selecting clients via prediction achieves higher accuracy than the random selection strategy. In brief, the proposed methods protect users’ privacy via FL. And the challenges of dynamical and heterogeneous stream data in indoor localization are addressed by the proposed methods which provide better personalization localization service for users than baseline methods.
- 5 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (11) , 10640-10654
Prediction Based Semi-Supervised Online Personalized Federated Learning for Indoor Localization
Fingerprint-based indoor localization has drawn increasing attention with the development of deep learning. Nevertheless, it faces challenges from frequent data collection and the corresponding exposure of privacy. Federated Learning (FL) is introduced into indoor localization recently for overcoming these challenges. However, most of the current FL-based indoor localization studies only focus on the static data distributions and ignore the fact that users have their preferred localization requirements. In this paper, two typical indoor localization scenarios are considered. Clients with various localization demands and data distributions collect online unlabeled data in Scenario I. For Scenario II, only one requesting user (RU) with high mobility applies for the localization service. A Prediction based Semi-supervised Online Personalized Federated Learning (PSO-PFL) is proposed for addressing these problems in the two scenarios. Experiments are conducted based on two real-world datasets. The experiment results show that PSO-PFL achieves higher personalization accuracy than centralized training and Federated Averaging, and utilizes unlabeled data efficiently. The strategy of selecting clients via prediction achieves higher accuracy than the random selection strategy. In brief, the proposed methods protect users’ privacy via FL. And the challenges of dynamical and heterogeneous stream data in indoor localization are addressed by the proposed methods which provide better personalization localization service for users than baseline methods.
- 14 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 26 (8) , 1794-1798
Multi-Level Federated Graph Learning and Self-Attention Based Personalized Wi-Fi Indoor Fingerprint Localization
Deep learning-based Wi-Fi indoor fingerprint localization, which requires a large received signal strength (RSS) dataset for training, has been widely studied. Federated learning (FL) is recently introduced into indoor localization in order to address the problem of data sharing without privacy disclosure. However, under the serious data heterogeneity of FL, the averaged model will perform worse for individual client. In this letter, a multi-level federated graph learning and self-attention based personalized indoor localization method is proposed to further capture the intrinsic features of RSS, and learn the aggregation manner of shared information uploaded by clients, with better personalization accuracy. The experimental results demonstrate that proposed methods achieve a higher personalized localization accuracy than compared personalized federated learning (PFL) methods, in most of the simulation settings.
- 14 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 26 (8) , 1794-1798
Multi-Level Federated Graph Learning and Self-Attention Based Personalized Wi-Fi Indoor Fingerprint Localization
Deep learning-based Wi-Fi indoor fingerprint localization, which requires a large received signal strength (RSS) dataset for training, has been widely studied. Federated learning (FL) is recently introduced into indoor localization in order to address the problem of data sharing without privacy disclosure. However, under the serious data heterogeneity of FL, the averaged model will perform worse for individual client. In this letter, a multi-level federated graph learning and self-attention based personalized indoor localization method is proposed to further capture the intrinsic features of RSS, and learn the aggregation manner of shared information uploaded by clients, with better personalization accuracy. The experimental results demonstrate that proposed methods achieve a higher personalized localization accuracy than compared personalized federated learning (PFL) methods, in most of the simulation settings.