Skip to main content
Publications lead hero image abstract pattern


Publication Date

Manuscript Submission Deadline

Special Issue

Call for Papers

Submit a Paper

Driven by privacy concerns and the promise of Deep Learning, there has been considerable amount of research that targets the applicability of Machine Learning (ML). The communication, network and service management fields are hungry for ML decision-making solutions to replace the traditional model-driven approaches to address the ever-growing complexity and heterogeneity of the modern systems.  In this context, interest in Federated Learning (FL) is rising to take into consideration the limitations of centralized systems for data analysis by using distributed on-site analysis for learning statistical models. It is a privacy preserving decentralized approach, which keeps raw data on devices and involves local Machine Learning training while eliminating data communication overhead. The training and testing occur not only on end devices, including personal computers, smartphones, and tablets, but also on edge devices that generate the data. A federation of the learned and shared models is then performed on a central server to aggregate and share the built knowledge among participants.

The existing Federated Learning schemes have limitations that require the development of novel solutions to better comprehend and improve the potential and propriety of applying Federated Learning for decision-making in various real-world applications. Existing challenges for employing Federated Learning include but not limited to network management, communication efficiency, client selection and scheduling, resource management, security concerns, privacy concerns, incentive mechanisms and service management and pricing. For addressing these challenges, there are various techniques as potential solutions, including data augmentation, active learning, multi-task learning, knowledge distillation, compression, game theory, trust and reputation, multi-objective optimization, reinforcement learning, transfer learning, blockchain, and many more. These solutions can potentially offer reliable, efficient, secure, and trustworthy collective learning for participants and service providers by deriving decisions using Federated Learning models for diversity of fields and applications.

IEEE Transactions on Network and Service Management (IEEE TNSM) is a premier journal for timely publication of archival research on the management of networks, systems, services and applications. This special issue will focus on the latest developments of Federated Learning in terms of System, Network, and Resource Management solutions supported with related case studies and experiments. We welcome submissions addressing the important challenges (see the non-exhaustive list of topics below) and presenting novel research or experimentation results with system or network related case studies. Survey papers that offer a perspective on related work and identify key challenges for future research will be considered as well. We look forward to your submissions!

Topics of Interest

In this Special Issue, we focus on cutting-edge research from academia and industry with an emphasis on the system, network, and resource management to realize the deployment of Federated Learning in practice and lay the groundwork for its future. Topics of interest for this Special Issue include, but are not limited, to the following:

  • Federated Machine Learning System Models & Design
  • Transfer Learning in Federated Learning
  • Knowledge Distillation in Federated learning
  • Analysis and Solutions for Non-IID Data
  • Service Pricing Models
  • Optimization Algorithms for Network Management in Federated Learning
  • Optimized Information Retrieval
  • Incentive Mechanisms for Federated Learning Participants
  • Federated Learning in Cloud/Fog/Edge Computing and Networks
  • Cloud/Fog/Edge Computing and Networks for Efficient Federated Learning
  • Deep Reinforcement Learning for Federated Learning Resource Management
  • Routing Schemes in Federated Learning
  • Federated Learning Client Selection and Scheduling
  • Platforms for Trust and Reputation Between Participants
  • Platforms Addressing Security Concerns in Federated Learning
  • Platforms Addressing Privacy Concerns in Federated Learning
  • Blockchain for Federated Learning
  • Applications of Federated Learning in Wireless Networks (5G, 6G), Internet of Things, Cloud/Fog/Edge Computing and Networks, Vehicular and Mobile Networks, Urban Environments, Smart Cities, Healthcare, etc.

Submission Guidelines

All papers should be submitted through the IEEE Transactions on Network and Service Management manuscript submission site. Authors must indicate in the submission cover letter that their manuscript is intended for the "the Latest Developments in Federated Learning for the Management of Networked Systems and Resources" special issue. View detailed author guidelines.

Important Dates

Paper Submission: 15 April 2024 (Extended Deadline)
Publication Date: 31 December 2024

Guest Editors

Azzam Mourad
Lebanese American University, Lebanon

Hadi Otrok
Khalifa University, UAE

Chadi Assi
Concordia University, Canada

Dario Rossi
Huawei, France

Paolo Bellavista
University of Bologna, Italy

Hakima Ould-Slimane
University of Quebec at Trois Rivieres, Canada

Xue Kaiping
University of Science and Technology, China