Jin Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jin Xie has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Weifeng Gao
Xidian University
12 shared publications - Hong Li
School of Mathematics and Statistics, Xidian University, Xian, China
11 shared publications - Sanyang Liu
School of Mathematics and Statistics, Xidian University, Xian, China
8 shared publications - Hao Dai
School of Aerospace Science and Technology, Xidian University, Xi’an, China
6 shared publications - Maoguo Gong
Xidian University, Xi'an, China
6 shared publications - Baosheng Li
Northwest A&F University
4 shared publications
Latest Publications
- 30 March 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17 (5) , 237
Manifold regularization based finite time distributed semi-supervised learning algorithm
- 30 March 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17 (5) , 237
Manifold regularization based finite time distributed semi-supervised learning algorithm
- Open Access
Global Fuzzy Adaptive Consensus for Uncertain Nonlinear Multi-Agent Systems with Unknown Control Directions
This paper investigates the consensus problem for a class of uncertain nonlinear multi-agent systems (MASs) subject to external disturbances with unknown control directions (UCDs). A novel control scheme integrating Nussbaum-type gain is proposed to actively compensate for UCDs, while fuzzy logic systems (FLSs) are embedded in a feed-forward compensator to approximate unknown nonlinear dynamics, thereby achieving global stability. The proposed distributed control laws ensure global asymptotic convergence for both first- and second-order MASs through Lyapunov stability analysis. By implementing a strategic reparameterization technique, this scheme systematically reduces computational complexity, requiring each agent to adapt only a minimal parameter set. Moreover, the framework is extended to address complex formation control tasks. Comprehensive simulations validate the efficacy of the theoretical findings.
Open AccessGlobal Fuzzy Adaptive Consensus for Uncertain Nonlinear Multi-Agent Systems with Unknown Control Directions
This paper investigates the consensus problem for a class of uncertain nonlinear multi-agent systems (MASs) subject to external disturbances with unknown control directions (UCDs). A novel control scheme integrating Nussbaum-type gain is proposed to actively compensate for UCDs, while fuzzy logic systems (FLSs) are embedded in a feed-forward compensator to approximate unknown nonlinear dynamics, thereby achieving global stability. The proposed distributed control laws ensure global asymptotic convergence for both first- and second-order MASs through Lyapunov stability analysis. By implementing a strategic reparameterization technique, this scheme systematically reduces computational complexity, requiring each agent to adapt only a minimal parameter set. Moreover, the framework is extended to address complex formation control tasks. Comprehensive simulations validate the efficacy of the theoretical findings.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 34 (5) , 1416-1429
A Distributed Cooperation-Competition Learning Algorithm With Neuro-Fuzzy Networks for Latency Communication Networks
As the foundation of next-generation wireless networks, distributed learning (DL) is expected to be integrated into 6 G communication networks, profoundly advancing the transformation of intelligent connectivity. However, network-induced delays critically degrade the performance of DL algorithms in practical deployments. Beyond the communication limitation, many emerging applications involve antagonistic interactions among agents, introducing additional complexity. To overcome these challenges, we propose a decentralized distributed cooperation–competition learning (DCCL) algorithm based on neuro-fuzzy networks, designed for latency communication networks. The algorithm innovatively employs the signed graph to naturally encode the coupling coopetition relationships among agents, and incorporates the delay model into its design. It demonstrates superior adaptability for DL problems with bimodal coalitional adversarial interactions in latency-prone mission-critical services. Moreover, we extend the neuro-fuzzy network into a distributed version, and the resulting distributed neuro-fuzzy model inherently preserves the interpretability characteristic and superior learning capability. Based on structural balance theory and discrete Lyapunov stability theory, we rigorously prove the convergence of the DCCL algorithm and derive an explicit sufficient condition in the form of a maximum allowable latency tolerance. The proposed algorithm benefits privacy protection by transmitting only model parameters. Experiments are conducted to validate the performance of the DCCL algorithm on several datasets for regression and classification. Furthermore, we discuss the limitations of the DCCL algorithm, providing a balanced perspective for future research.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 34 (5) , 1416-1429
A Distributed Cooperation-Competition Learning Algorithm With Neuro-Fuzzy Networks for Latency Communication Networks
As the foundation of next-generation wireless networks, distributed learning (DL) is expected to be integrated into 6 G communication networks, profoundly advancing the transformation of intelligent connectivity. However, network-induced delays critically degrade the performance of DL algorithms in practical deployments. Beyond the communication limitation, many emerging applications involve antagonistic interactions among agents, introducing additional complexity. To overcome these challenges, we propose a decentralized distributed cooperation–competition learning (DCCL) algorithm based on neuro-fuzzy networks, designed for latency communication networks. The algorithm innovatively employs the signed graph to naturally encode the coupling coopetition relationships among agents, and incorporates the delay model into its design. It demonstrates superior adaptability for DL problems with bimodal coalitional adversarial interactions in latency-prone mission-critical services. Moreover, we extend the neuro-fuzzy network into a distributed version, and the resulting distributed neuro-fuzzy model inherently preserves the interpretability characteristic and superior learning capability. Based on structural balance theory and discrete Lyapunov stability theory, we rigorously prove the convergence of the DCCL algorithm and derive an explicit sufficient condition in the form of a maximum allowable latency tolerance. The proposed algorithm benefits privacy protection by transmitting only model parameters. Experiments are conducted to validate the performance of the DCCL algorithm on several datasets for regression and classification. Furthermore, we discuss the limitations of the DCCL algorithm, providing a balanced perspective for future research.
- 13 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (6) , 3210-3223
Evolutionary Multiobjective Neural Architecture Search for Binary Neural Networks by Two-Stage Optimization
Binary neural networks (BNNs) have been applied in limited resources and mobile devices because of their extreme model compression ability. However, manually designing suitable architectures is challenging given the specialized structure of binarized operations. Neural architecture search (NAS) provides a promising approach for designing high-performance BNN architectures. In practice, various situations require networks with different parameter sizes and performance levels. Therefore, this article proposes a multiobjective evolutionary NAS algorithm for BNNs based on a two-stage training strategy (MO-TS-BNAS) to solve these problems. First, the ApproxSign function is used to approximate the gradient error in the training of BNNs. To avoid the small model trap problem, two auxiliary objectives are introduced in nondominated sorting to retain larger models with similar errors. Then, a two-stage training strategy with flexible use of auxiliary objectives is proposed, forming the selection mechanism in environmental selection. The path dropout method is used in the second stage to prevent hypernetwork overfitting. In addition, the mini-batch gradient descent strategy is improved to speed up individual architecture evaluation and reduce time cost in the search process. Finally, the full precision baseline search space is binarized for general experimental comparison. Our MO-TS-BNAS algorithm balances the two different objective functions of the model size and error. A large number of experiments are carried out on the CIFAR10 and ImageNet datasets, and the results show the effectiveness of the proposed method.
- 13 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 56 (6) , 3210-3223
Evolutionary Multiobjective Neural Architecture Search for Binary Neural Networks by Two-Stage Optimization
Binary neural networks (BNNs) have been applied in limited resources and mobile devices because of their extreme model compression ability. However, manually designing suitable architectures is challenging given the specialized structure of binarized operations. Neural architecture search (NAS) provides a promising approach for designing high-performance BNN architectures. In practice, various situations require networks with different parameter sizes and performance levels. Therefore, this article proposes a multiobjective evolutionary NAS algorithm for BNNs based on a two-stage training strategy (MO-TS-BNAS) to solve these problems. First, the ApproxSign function is used to approximate the gradient error in the training of BNNs. To avoid the small model trap problem, two auxiliary objectives are introduced in nondominated sorting to retain larger models with similar errors. Then, a two-stage training strategy with flexible use of auxiliary objectives is proposed, forming the selection mechanism in environmental selection. The path dropout method is used in the second stage to prevent hypernetwork overfitting. In addition, the mini-batch gradient descent strategy is improved to speed up individual architecture evaluation and reduce time cost in the search process. Finally, the full precision baseline search space is binarized for general experimental comparison. Our MO-TS-BNAS algorithm balances the two different objective functions of the model size and error. A large number of experiments are carried out on the CIFAR10 and ImageNet datasets, and the results show the effectiveness of the proposed method.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (5) , 6688-6704
Decentralized Federated Learning Over Time-Varying and Heterogeneous Mobile Computing Networks
We consider decentralized federated learning (DFL) in mobile computing networks (MCNs), where dynamically changing neighborhood sets among devices arise from mobility and environmental perturbations. The time-varying topology coupled with inherent system heterogeneity poses significant challenges to achieve stable and efficient convergence in DFL. However, existing studies rarely consider both dynamic connectivity and statistical heterogeneity. To close this gap, this paper proposes a novel DFL framework enhanced with topology learning (DFL-TL) to mitigate the spatio-temporal volatility induced by MCNs, where each mobile device faces coupled constraints on its temporal windows for local updates and spatial scopes for model interaction. We introduce a new bounded neighborhood heterogeneity to jointly measure and constrain both the inter-device heterogeneity and the spectral properties of the topologies. Additionally, we formulate a mixed-integer nonlinear programming (MINLP) problem to jointly optimize learning costs and neighborhood heterogeneity. Through problem decomposition, DFL-TL efficiently identifies optimal resource allocations and adaptive mixing matrices, thereby enabling the selection of optimal training time windows while reducing the adverse effects of dynamic topologies in heterogeneous networks. Furthermore, we establish the iteration complexity of DFL-TL under non-convex settings and show that solving the proposed MINLP formulation leads to a tighter convergence bound. Extensive experiments demonstrate that DFL-TL achieves a faster convergence performance and reduces the wall-clock training time compared to the state-of-the-art baselines.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (5) , 6688-6704
Decentralized Federated Learning Over Time-Varying and Heterogeneous Mobile Computing Networks
We consider decentralized federated learning (DFL) in mobile computing networks (MCNs), where dynamically changing neighborhood sets among devices arise from mobility and environmental perturbations. The time-varying topology coupled with inherent system heterogeneity poses significant challenges to achieve stable and efficient convergence in DFL. However, existing studies rarely consider both dynamic connectivity and statistical heterogeneity. To close this gap, this paper proposes a novel DFL framework enhanced with topology learning (DFL-TL) to mitigate the spatio-temporal volatility induced by MCNs, where each mobile device faces coupled constraints on its temporal windows for local updates and spatial scopes for model interaction. We introduce a new bounded neighborhood heterogeneity to jointly measure and constrain both the inter-device heterogeneity and the spectral properties of the topologies. Additionally, we formulate a mixed-integer nonlinear programming (MINLP) problem to jointly optimize learning costs and neighborhood heterogeneity. Through problem decomposition, DFL-TL efficiently identifies optimal resource allocations and adaptive mixing matrices, thereby enabling the selection of optimal training time windows while reducing the adverse effects of dynamic topologies in heterogeneous networks. Furthermore, we establish the iteration complexity of DFL-TL under non-convex settings and show that solving the proposed MINLP formulation leads to a tighter convergence bound. Extensive experiments demonstrate that DFL-TL achieves a faster convergence performance and reduces the wall-clock training time compared to the state-of-the-art baselines.
- Open Access
Decentralized Semantic Federated Learning for Real-Time Public Safety Tasks: Challenges, Methods, and Directions
Public safety tasks rely on the collaborative functioning of multiple edge devices (MEDs) and base stations (BSs) in different regions, consuming significant communication energy and computational resources to execute critical operations like fire monitoring and rescue missions. Traditional federated edge computing (EC) methods require frequent central communication, consuming substantial energy and struggling with resource heterogeneity across devices, networks, and data. To this end, this paper introduces a decentralized semantic federated learning (DSFL) framework tailored for large-scale wireless communication systems and heterogeneous MEDs. The framework incorporates a hierarchical semantic communication (SC) scheme to extend EC coverage and reduce communication overhead. Specifically, the lower layer optimizes intra-BS communication through task-specific encoding and selective transmission under constrained networks, while the upper layer ensures robust inter-BS communication via semantic aggregation and distributed consensus across different regions. To further balance communication costs and semantic accuracy, an energy-efficient aggregation scheme is developed for both intra-BS and inter-BS communication. The effectiveness of the DSFL framework is demonstrated through a case study using the BoWFire dataset, showcasing its potential in real-time fire detection scenarios. Finally, we outlines open issues for edge intelligence and SC in public safety tasks.
Open AccessDecentralized Semantic Federated Learning for Real-Time Public Safety Tasks: Challenges, Methods, and Directions
Public safety tasks rely on the collaborative functioning of multiple edge devices (MEDs) and base stations (BSs) in different regions, consuming significant communication energy and computational resources to execute critical operations like fire monitoring and rescue missions. Traditional federated edge computing (EC) methods require frequent central communication, consuming substantial energy and struggling with resource heterogeneity across devices, networks, and data. To this end, this paper introduces a decentralized semantic federated learning (DSFL) framework tailored for large-scale wireless communication systems and heterogeneous MEDs. The framework incorporates a hierarchical semantic communication (SC) scheme to extend EC coverage and reduce communication overhead. Specifically, the lower layer optimizes intra-BS communication through task-specific encoding and selective transmission under constrained networks, while the upper layer ensures robust inter-BS communication via semantic aggregation and distributed consensus across different regions. To further balance communication costs and semantic accuracy, an energy-efficient aggregation scheme is developed for both intra-BS and inter-BS communication. The effectiveness of the DSFL framework is demonstrated through a case study using the BoWFire dataset, showcasing its potential in real-time fire detection scenarios. Finally, we outlines open issues for edge intelligence and SC in public safety tasks.
- 14 March 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 278
Neural architecture search with integrated template-modules for efficient defect detection
- 14 March 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 278
Neural architecture search with integrated template-modules for efficient defect detection
- 16 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (1) , 884-893
Federated Multidiscriminators Multigenerators for Heterogeneous Industrial IoT
Federated learning (FL) is a distributed learning paradigm that leverages local updates and parameter sharing to address privacy concerns in Industrial Internet of Things (IIoT) environments. The presence of statistical heterogeneity among IIoT devices poses significant challenges for FL, impacting convergence and model performance. Although previous studies have attempted to mitigate this issue, a fundamental solution remains elusive. To address this, we propose a novel approach called federated multidiscriminators multigenerators generative adversarial network (FedMDMG-GAN), which employs a distributed generative adversarial network (GAN). IIoT devices concurrently train local generators and discriminators to generate data with global information. The server then aggregates parameters and redistributes them to the devices to refine local GANs. In addition, we introduce a proximal term for global aggregation to enhance convergence. Theoretical analysis suggests that the FedMDMG-GAN algorithm can asymptotically converge to a stable point. Qualitative assessments demonstrate that our method can generate images closely resembling real data with comprehensive global information. Quantitative results indicate that FedMDMG-GAN outperforms vanilla FL and state-of-the-art methods.
- 16 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (1) , 884-893
Federated Multidiscriminators Multigenerators for Heterogeneous Industrial IoT
Federated learning (FL) is a distributed learning paradigm that leverages local updates and parameter sharing to address privacy concerns in Industrial Internet of Things (IIoT) environments. The presence of statistical heterogeneity among IIoT devices poses significant challenges for FL, impacting convergence and model performance. Although previous studies have attempted to mitigate this issue, a fundamental solution remains elusive. To address this, we propose a novel approach called federated multidiscriminators multigenerators generative adversarial network (FedMDMG-GAN), which employs a distributed generative adversarial network (GAN). IIoT devices concurrently train local generators and discriminators to generate data with global information. The server then aggregates parameters and redistributes them to the devices to refine local GANs. In addition, we introduce a proximal term for global aggregation to enhance convergence. Theoretical analysis suggests that the FedMDMG-GAN algorithm can asymptotically converge to a stable point. Qualitative assessments demonstrate that our method can generate images closely resembling real data with comprehensive global information. Quantitative results indicate that FedMDMG-GAN outperforms vanilla FL and state-of-the-art methods.