Guest Editor(s)
Dr. Yi Liu
Email: yiliu247@cityu.edu.hk
Affiliation: Department of Computer Science, City University of Hong Kong, Hong Kong, China
Homepage:
Research Interests: federated learning, trustworthy AI, embodied AI
Prof. Pengfei Zhang
Email: zpf.bupt@bupt.cn
Affiliation: School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, China
Homepage:
Research Interests: data privacy protection
Prof. Jinchao Chen
Email: cjc@nwpu.edu.cn
Affiliation: School of Computer Science, Northwestern Polytechnical University, Xi'an, China
Homepage:
Research Interests: federated learning, multi agent
Dr. Zijian Li
Email: lizj@dlmu.edu.cn
Affiliation: College of Artificial Intelligence, Dalian Maritime University, Dalian, China
Homepage:
Research Interests: edge intelligence, federated learning, LLM
Prof. Jie Chen
Email: chenjie2025@ustc.edu.cn
Affiliation: Department of Automation, University of Science and Technology of China, Hefei, China
Homepage:
Research Interests: game theory, multi-agent cooperation, LLM
Summary
Multi-agent systems enable autonomous agents to collaborate in perception, learning, decision-making, and execution, and have been widely adopted in robotics, intelligent transportation, smart manufacturing, edge computing, and industrial automation. However, centralized learning requires agents to upload local data, creating privacy risks, communication bottlenecks, and single points of failure.
Federated learning allows multiple agents to jointly train models without sharing raw data. Combined with data mining, it supports distributed knowledge discovery, collaborative intelligence, personalized decision-making, and privacy-preserving analytics. This integration provides a practical foundation for scalable and secure multi-agent collaboration.
Despite its potential, federated learning in multi-agent systems faces major challenges, including non-IID data, heterogeneous resources, dynamic participation, limited communication, adversarial agents, privacy leakage, and model poisoning. Robust, efficient, and trustworthy learning mechanisms are therefore essential.
This special issue focuses on federated learning for multi-agent systems and data mining. Topics of interest include, but are not limited to:
· Federated learning architectures for multi-agent systems
· Decentralized and asynchronous federated learning
· Federated reinforcement learning and collaborative decision-making
· Personalized federated learning for heterogeneous agents
· Federated data mining and knowledge discovery
· Communication-efficient and resource-aware learning
· Privacy-preserving learning and secure aggregation
· Robust federated learning against poisoning and Byzantine attacks
· Trust, reputation, and incentive mechanisms
· Multimodal and heterogeneous data fusion
· Federated anomaly detection and behavior analysis
· Edge intelligence for robots, vehicles, drones, and industrial agents
· Benchmarking, evaluation, and real-world applications
Keywords
federated learning, multi-agent systems, data mining, distributed intelligence, privacy protection, secure aggregation, federated reinforcement learning, edge intelligence, trustworthy AI
Login
Register
Submit a Paper
Propose a Special lssue