Xiongtao Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiongtao Zhang has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Ji Wang
National university of defense technology, Changsha, China
12 shared publications - Weidong Bao
College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
11 shared publications - Xiaomin Zhu
Strategic Assessments and Consultation Institute, Academy of Military Science, Beijing 100091, China
7 shared publications - Jingxuan Zhou
National Key Laboratory of Big Data and Decision, National University of Defense Technology, Changsha, Hunan, China
4 shared publications - Yaohong Zhang
Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China
3 shared publications - Dayu Zhang
Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14722-14730
FedMMDP: A Federated Multimodal Domain Personalization Framework with Modality Alignment and Privacy Preservation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14722-14730
Open AccessFedMMDP: A Federated Multimodal Domain Personalization Framework with Modality Alignment and Privacy Preservation
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2569-2580
Unveiling and Mitigating Untargeted Poisoning Attacks on Federated Knowledge Graph Embedding
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2569-2580
Open AccessUnveiling and Mitigating Untargeted Poisoning Attacks on Federated Knowledge Graph Embedding
- Open Access
A Review of Federated Large Language Models for Industry 4.0
Industry 4.0 envisions a highly interconnected, autonomous manufacturing ecosystem enabled by the Industrial Internet of Things, Cyber-Physical Systems, and Artificial Intelligence. The emergence of large language models introduces new capabilities for semantic-aware decision-making, cross-domain knowledge integration, and intelligent automation. However, privacy, security, and regulatory constraints often isolate industrial data, impeding the scalability of LLMs in manufacturing. Federated learning addresses this by enabling decentralized LLM optimization without exposing raw data. This paper presents a comprehensive review of recent federated large language model research with a focus on industrial feasibility, comparing enabling techniques, system designs, and deployment strategies. Based on existing studies, forward-looking analyses are provided to highlight potential challenges and trade-offs in practical adoption, including computation and communication overheads, synchronization in large-scale federations, and system robustness. By bridging foundational methods with emerging industrial scenarios, we finally discuss the significant challenges associated with deploying federated large language models in complex industrial environments and outline a future research agenda.
Open AccessA Review of Federated Large Language Models for Industry 4.0
Industry 4.0 envisions a highly interconnected, autonomous manufacturing ecosystem enabled by the Industrial Internet of Things, Cyber-Physical Systems, and Artificial Intelligence. The emergence of large language models introduces new capabilities for semantic-aware decision-making, cross-domain knowledge integration, and intelligent automation. However, privacy, security, and regulatory constraints often isolate industrial data, impeding the scalability of LLMs in manufacturing. Federated learning addresses this by enabling decentralized LLM optimization without exposing raw data. This paper presents a comprehensive review of recent federated large language model research with a focus on industrial feasibility, comparing enabling techniques, system designs, and deployment strategies. Based on existing studies, forward-looking analyses are provided to highlight potential challenges and trade-offs in practical adoption, including computation and communication overheads, synchronization in large-scale federations, and system robustness. By bridging foundational methods with emerging industrial scenarios, we finally discuss the significant challenges associated with deploying federated large language models in complex industrial environments and outline a future research agenda.
- 12 September 2025
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 16 (12) , 10403-10420
Multi-task federated learning with encoder–decoder structure: enabling collaborative learning across different tasks
- 12 September 2025
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 16 (12) , 10403-10420
Multi-task federated learning with encoder–decoder structure: enabling collaborative learning across different tasks
- Open Access
Multi-task Federated Learning with Encoder-Decoder Structure: Enabling Collaborative Learning Across Different Tasks
Federated learning has been extensively studied and applied due to its ability to ensure data security in distributed environments while building better models. However, clients participating in federated learning still face limitations, as clients with different structures or tasks cannot participate in learning together. In view of this, constructing a federated learning framework that allows collaboration between clients with different model structures and performing different tasks, enabling them to share valuable knowledge to enhance model efficiency, holds significant practical implications for the widespread application of federated learning. To achieve this goal, we propose a multi-task federated learning with encoder-decoder structure (M-Fed). Specifically, given the widespread adoption of the encoder-decoder architecture in current models, we leverage this structure to share intra-task knowledge through traditional federated learning methods and extract general knowledge from the encoder to achieve cross-task knowledge sharing. The training process is similar to traditional federated learning, and we incorporate local decoder and global decoder information into the loss function. The local decoder iteratively updates and gradually approaches the global decoder until sufficient cross-task knowledge sharing is achieved. Our method is lightweight and modular, demonstrating innovation compared to previous research. It enables clients performing different tasks to share general knowledge while maintaining the efficiency of traditional federated learning systems. We conducted experiments on two widely used benchmark datasets to verify the feasibility of M-Fed and compared it with traditional methods. The experimental results demonstrate the effectiveness of M-Fed in multi-task federated learning.
Open AccessMulti-task Federated Learning with Encoder-Decoder Structure: Enabling Collaborative Learning Across Different Tasks
Federated learning has been extensively studied and applied due to its ability to ensure data security in distributed environments while building better models. However, clients participating in federated learning still face limitations, as clients with different structures or tasks cannot participate in learning together. In view of this, constructing a federated learning framework that allows collaboration between clients with different model structures and performing different tasks, enabling them to share valuable knowledge to enhance model efficiency, holds significant practical implications for the widespread application of federated learning. To achieve this goal, we propose a multi-task federated learning with encoder-decoder structure (M-Fed). Specifically, given the widespread adoption of the encoder-decoder architecture in current models, we leverage this structure to share intra-task knowledge through traditional federated learning methods and extract general knowledge from the encoder to achieve cross-task knowledge sharing. The training process is similar to traditional federated learning, and we incorporate local decoder and global decoder information into the loss function. The local decoder iteratively updates and gradually approaches the global decoder until sufficient cross-task knowledge sharing is achieved. Our method is lightweight and modular, demonstrating innovation compared to previous research. It enables clients performing different tasks to share general knowledge while maintaining the efficiency of traditional federated learning systems. We conducted experiments on two widely used benchmark datasets to verify the feasibility of M-Fed and compared it with traditional methods. The experimental results demonstrate the effectiveness of M-Fed in multi-task federated learning.
- Open Access
- 17 March 2025
- Published by Auckland University of Technology (AUT) Library
- Vol. 1
Doc2Event: Extracting Chinese Document-Level Events into Generation Models
Current methodologies for document-level event extraction, particularly within Chinese textual data, face significant challenges, such as the extraction of isolated events and the imprecise delineation of event interrelationships. The advent of large language models, fortunately, offers a promising frontier for enhancing event extraction capabilities. In light of this, this study proposes an innovative framework for the extraction of multiple events that effectively mitigates these limitations. The proposed framework employs the Entity-based Directed Acyclic Graph(EDAG) to accurately model and articulate serialization relationships among events in Chinese documents. Furthermore, it incorporates prefix prompt, thereby broadening the applicability of generative models to document-level multi-event extraction tasks. Empirical evaluations of the proposed framework were conducted using the mT5 model on challenging datasets, including the DuEE-Fin dataset from the financial domain and the FNDEE dataset from the military domain.
- 17 March 2025
- Published by Auckland University of Technology (AUT) Library
- Vol. 1
Open AccessDoc2Event: Extracting Chinese Document-Level Events into Generation Models
Current methodologies for document-level event extraction, particularly within Chinese textual data, face significant challenges, such as the extraction of isolated events and the imprecise delineation of event interrelationships. The advent of large language models, fortunately, offers a promising frontier for enhancing event extraction capabilities. In light of this, this study proposes an innovative framework for the extraction of multiple events that effectively mitigates these limitations. The proposed framework employs the Entity-based Directed Acyclic Graph(EDAG) to accurately model and articulate serialization relationships among events in Chinese documents. Furthermore, it incorporates prefix prompt, thereby broadening the applicability of generative models to document-level multi-event extraction tasks. Empirical evaluations of the proposed framework were conducted using the mT5 model on challenging datasets, including the DuEE-Fin dataset from the financial domain and the FNDEE dataset from the military domain.
- Open Access
FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation
Federated Reinforcement Learning (FedRL) improves sample efficiency while preserving privacy; however, most existing studies assume homogeneous agents, limiting its applicability in real-world scenarios. This paper investigates FedRL in black-box settings with heterogeneous agents, where each agent employs distinct policy networks and training configurations without disclosing their internal details. Knowledge Distillation (KD) is a promising method for facilitating knowledge sharing among heterogeneous models, but it faces challenges related to the scarcity of public datasets and limitations in knowledge representation when applied to FedRL. To address these challenges, we propose Federated Heterogeneous Policy Distillation (FedHPD), which solves the problem of heterogeneous FedRL by utilizing action probability distributions as a medium for knowledge sharing. We provide a theoretical analysis of FedHPD's convergence under standard assumptions. Extensive experiments corroborate that FedHPD shows significant improvements across various reinforcement learning benchmark tasks, further validating our theoretical findings. Moreover, additional experiments demonstrate that FedHPD operates effectively without the need for an elaborate selection of public datasets.
Open AccessFedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation
Federated Reinforcement Learning (FedRL) improves sample efficiency while preserving privacy; however, most existing studies assume homogeneous agents, limiting its applicability in real-world scenarios. This paper investigates FedRL in black-box settings with heterogeneous agents, where each agent employs distinct policy networks and training configurations without disclosing their internal details. Knowledge Distillation (KD) is a promising method for facilitating knowledge sharing among heterogeneous models, but it faces challenges related to the scarcity of public datasets and limitations in knowledge representation when applied to FedRL. To address these challenges, we propose Federated Heterogeneous Policy Distillation (FedHPD), which solves the problem of heterogeneous FedRL by utilizing action probability distributions as a medium for knowledge sharing. We provide a theoretical analysis of FedHPD's convergence under standard assumptions. Extensive experiments corroborate that FedHPD shows significant improvements across various reinforcement learning benchmark tasks, further validating our theoretical findings. Moreover, additional experiments demonstrate that FedHPD operates effectively without the need for an elaborate selection of public datasets.
- 11 September 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 304
Structural graph federated learning: Exploiting high-dimensional information of statistical heterogeneity
- 11 September 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 304
Structural graph federated learning: Exploiting high-dimensional information of statistical heterogeneity
- 12 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (1) , 88-101
Improving Generalization and Personalization in Model-Heterogeneous Federated Learning
Conventional federated learning (FL) assumes the homogeneity of models, necessitating clients to expose their model parameters to enhance the performance of the server model. However, this assumption cannot reflect real-world scenarios. Sharing models and parameters raises security concerns for users, and solely focusing on the server-side model neglects clients’ personalization requirements, potentially impeding expected performance improvements of users. On the other hand, prioritizing personalization may compromise the generalization of the server model, thereby hindering extensive knowledge migration. To address these challenges, we put forth an important problem: How can FL ensure both generalization and personalization when clients’ models are heterogeneous? In this work, we introduce FedTED, which leverages a twin-branch structure and data-free knowledge distillation (DFKD) to address the challenges posed by model heterogeneity and diverse objectives in FL. The employed techniques in FedTED yield significant improvements in both personalization and generalization, while effectively coordinating the updating process of clients’ heterogeneous models and successfully reconstructing a satisfactory global model. Our empirical evaluation demonstrates that FedTED outperforms many representative algorithms, particularly in scenarios where clients’ models are heterogeneous, achieving a remarkable 19.37% enhancement in generalization performance and up to 9.76% improvement in personalization performance.
- 12 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (1) , 88-101
Improving Generalization and Personalization in Model-Heterogeneous Federated Learning
Conventional federated learning (FL) assumes the homogeneity of models, necessitating clients to expose their model parameters to enhance the performance of the server model. However, this assumption cannot reflect real-world scenarios. Sharing models and parameters raises security concerns for users, and solely focusing on the server-side model neglects clients’ personalization requirements, potentially impeding expected performance improvements of users. On the other hand, prioritizing personalization may compromise the generalization of the server model, thereby hindering extensive knowledge migration. To address these challenges, we put forth an important problem: How can FL ensure both generalization and personalization when clients’ models are heterogeneous? In this work, we introduce FedTED, which leverages a twin-branch structure and data-free knowledge distillation (DFKD) to address the challenges posed by model heterogeneity and diverse objectives in FL. The employed techniques in FedTED yield significant improvements in both personalization and generalization, while effectively coordinating the updating process of clients’ heterogeneous models and successfully reconstructing a satisfactory global model. Our empirical evaluation demonstrates that FedTED outperforms many representative algorithms, particularly in scenarios where clients’ models are heterogeneous, achieving a remarkable 19.37% enhancement in generalization performance and up to 9.76% improvement in personalization performance.
- 31 July 2024
- Published by Elsevier in Future Generation Computer Systems
- Vol. 161, 638-654
Self-adaptive asynchronous federated optimizer with adversarial sharpness-aware minimization
- 31 July 2024
- Published by Elsevier in Future Generation Computer Systems
- Vol. 161, 638-654
Self-adaptive asynchronous federated optimizer with adversarial sharpness-aware minimization