Yuwei Wang

Yuwei Wang

Auto-generated profile, based on publicly available information

Yuwei Wang

College of Control Science and Engineering, Zhejiang University, Hangzhou, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 October 2021 in IEEE Journal on Selected Areas in Communications
Verified
Journal Article
Closed access
PSPeng Sun
Peng Sun
HCHaoxuan Che
Haoxuan Che
ZWZhibo Wang
Zhibo Wang
YWYuwei Wang
Yuwei Wang
TWTao Wang
Tao Wang
HSHuajie Shao
Huajie Shao
Federated learning (FL) is a privacy-preserving distributed machine learning framework, which involves training statistical models over a number of mobile users (i.e., workers) while keeping data localized. However, recent works have demonstrated that workers engaged in FL are still susceptible to advanced inference attacks when sharing model updates or gradients, which would discourage them from participating. Most of the existing incentive mechanisms for FL mainly account for workers’ resource cost, while the cost incurred by potential privacy leakage resulting from inference attacks has rarely been incorporated. To address these issues, in this paper, we propose a contract-based personalized privacy-preserving incentive for FL, named Pain-FL, to provide customized payments for workers with different privacy preferences as compensation for privacy leakage cost while ensuring satisfactory convergence performance of FL models. The core idea of Pain-FL is that each worker agrees on a customized contract, which specifies a kind of privacy-preserving level (PPL) and the corresponding payment, with the server in each round of FL. Then, the worker perturbs her calculated stochastic gradients to be uploaded with that PPL in exchange for that payment. In particular, we respectively derive a set of optimal contracts analytically under both complete and incomplete information models, which could optimize the convergence performance of the finally learned global model, while bearing some desired economic properties, i.e., budget feasibility, individual rationality, and incentive compatibility. An exhaustive experimental evaluation of Pain-FL is conducted, and the results corroborate its practicability and effectiveness.

20 December 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
YWYuwei Wang
Yuwei Wang
PSPeng Sun
Peng Sun
ZWZhi Wang
Zhi Wang
Estimating the state (i.e., determining the position and orientation) of a rigid body (RB) is a key enabler technology for many applications (e.g., vehicle motion control and autonomous driving). Thus, rigid body localization (RBL), which can obtain both positions and poses of RBs, has drawn great attention recently. Most existing RBL methods mainly focus on estimating a single RB's state. However, the multi-agent scenario, which can be found in many applications like vehicleto-vehicle communication, has not been explicitly accounted for. Moreover, these methods undergo significant performance degradation when the communication conditions between sensors and anchors are poor. In this work, we propose a cooperative rigid body localization (CRBL) framework, which additionally leverages the interactions among RBs to achieve accurate and robust state estimation of multiple RBs. To this end, we need to figure out two key questions: 1) how to assess the attainable performance of CRBL; 2) how to use the newly introduced measurements among RBs to enhance the estimation performance. To answer the two questions, we first perform the CramerRao lower bound (CRLB) analysis for the CRBL framework to characterize the performance improvement. Theoretical analysis shows that CRBL has a lower error bound than the conventional RBL framework. Furthermore, we propose two efficient CRBL algorithms. The first one is a lightweight method based on the weighted least squares, named WLS-CRBL, which is an optimal algorithm over the small noise region and is computationally efficient. The second one is implemented by the semi-definite relaxation (SDR) technique named SDR-CRBL, aiming to achieve robust estimation when the noise is high. Numerical experiments show that the proposed methods can achieve their theoretical performance and outperform the conventional RBL algorithms, especially in the case of poor communications between sensors and anchors.

29 May 2025 in IEEE Journal on Selected Areas in Communications
Verified
Journal Article
Closed access
PSPeng Sun
Peng Sun
GLGuocheng Liao
Guocheng Liao
JHJianwei Huang
Jianwei Huang
XLXiang Li
Xiang Li
YWYuwei Wang
Yuwei Wang
XCXu Chen
Xu Chen
Federated learning (FL) has been extensively applied in industrial cyber-physical systems (ICPSs) to develop powerful models for complex industrial tasks (e.g., fault diagnosis), while safeguarding industrial data confidentiality. Asynchronous federated learning (AFL) effectively mitigates the straggler issue in the synchronous paradigm by aggregating client models in a first-come-first-served manner. Proper client selection is crucial for achieving efficient model training in AFL. A widely adopted model for implementing client selection in AFL is multi-armed bandit (MAB), which models client selection as arm pulling. Existing MAB-based client selection schemes overlook practical scenarios where direct client-server communications are unfavorable or unavailable (for example, in ICPSs such as mines, where communication infrastructure is underdeveloped, direct client-server communication is often unreliable or even unfeasible). In such cases, the server needs to incentivize self-interested relays to perform arm-pulling actions, including selecting the right client and relaying the communication from the selected client to the server. This paper proposes the first framework of incentivized online client selection for AFL. The design and optimization of such a framework involve significant challenges due to the tight coupling between unknown client behavior and private relay cost. To circumvent this challenge, we adopt the dual-based method and construct a special Lagrangian function that incorporates client behavior learning and relay cost revelation, and utilize it to design a socially-optimal mechanism for the framework. Our mechanism satisfies several desirable properties, including voluntary participation, incentive compatibility, relay utilization fairness, and client participation fairness. The proposed mechanism achieves the same asymptotic performance as the state-of-the-art benchmark that requires additional information. Furthermore, our analysis reveals that more available relays bring our mechanism closer to the theoretical upper bound of social performance. Numerical results demonstrate that our proposed mechanism achieves up to 85% and 99% of the social welfare obtained by the benchmarks.

9 November 2023 in arXiv
Verified
Preprint
Open access
PDF file
ZWZhiyuan Wu
Zhiyuan Wu
SSSheng Sun
Sheng Sun
YWYuwei Wang
Yuwei Wang
MLMin Liu
Min Liu
QPQuyang Pan
Quyang Pan
QLQingxiang Liu
Qingxiang Liu
Federated learning (FL) is a privacy-preserving machine learning paradigm in which the server periodically aggregates local model parameters from clients without assembling their private data. Constrained communication and personalization requirements pose severe challenges to FL. Federated distillation (FD) is proposed to simultaneously address the above two problems, which exchanges knowledge between the server and clients, supporting heterogeneous local models while significantly reducing communication overhead. However, most existing FD methods require a proxy dataset, which is often unavailable in reality. A few recent proxy-data-free FD approaches can eliminate the need for additional public data, but suffer from remarkable discrepancy among local knowledge due to client-side model heterogeneity, leading to ambiguous representation on the server and inevitable accuracy degradation. To tackle this issue, we propose a proxy-data-free FD algorithm based on distributed knowledge congruence (FedDKC). FedDKC leverages well-designed refinement strategies to narrow local knowledge differences into an acceptable upper bound, so as to mitigate the negative effects of knowledge incongruence. Specifically, from perspectives of peak probability and Shannon entropy of local knowledge, we design kernel-based knowledge refinement (KKR) and searching-based knowledge refinement (SKR) respectively, and theoretically guarantee that the refined-local knowledge can satisfy an approximately-similar distribution and be regarded as congruent. Extensive experiments conducted on three common datasets demonstrate that our proposed FedDKC significantly outperforms the state-of-the-art on various heterogeneous settings while evidently improving the convergence speed.

10 November 2023 in Electronics Letters
Verified
Journal Article
Open access
YWYuwei Wang
Yuwei Wang
PSPeng Sun
Peng Sun
ZWZhi Wang
Zhi Wang
The rigid body localization (RBL) technique is capable of estimating the state of a rigid body, including its translation and orientation, by utilizing the interactions between sensors and landmarks. The prevalent RBL methods employ precise time‐of‐flight measurements (or range measurements) to estimate the state. However, the clock offsets in range measurements in asynchronous networks are unavoidable, leading to performance degradation for state estimators. Therefore, range difference measurements have been adopted to solve the RBL problem. However, existing approaches struggle to achieve desirable performance while maintaining computational efficiency. To address this issue, a new closed‐form state estimator for asynchronous networks is introduced. The proposed algorithm leverages the Taylor‐series expansion technique to enhance accuracy while keeping computational overhead low. Numerical experiments demonstrate that the proposed method achieves state‐of‐the‐art performance with high computational efficiency under small Gaussian noises.