Federated Learning and Its Application

Dear Colleagues,

Federated learning has emerged as a promising distributed machine learning paradigm that enables collaborative model training across multiple participants without requiring the sharing of raw data. By keeping data localized and exchanging only model parameters or intermediate updates, federated learning offers inherent advantages in privacy preservation, data security, regulatory compliance, and cross-organizational collaboration. This paradigm effectively addresses key limitations of traditional centralized learning approaches, including data silos, privacy leakage risks, and increasingly strict data protection regulations.

With the rapid development of edge computing, mobile intelligence, and artificial intelligence technologies, federated learning has attracted substantial attention in both academia and industry. It has shown strong potential in varied application domains, such as the Internet of Things, edge intelligence, healthcare systems, financial services, smart cities, and autonomous driving. These application scenarios often involve distributed, resource-constrained, and privacy-sensitive environments, which further highlight the practical importance of federated learning. Despite its promising prospects, the deployment of federated learning in real-world complex environments remains challenging. Issues such as limited communication efficiency, system and device heterogeneity, non-independent and identically distributed data, scalability, robustness, and security continue to hinder its practical adoption. Furthermore, data owned by different participants often vary in collection conditions, scale, and feature distributions and may suffer from noise, incompleteness, or inconsistency, which increases the complexity of model training and aggregation. Addressing these challenges requires systematic and in-depth research across algorithmic, system-level, and application-oriented perspectives.

This Special Issue will provide a high-quality academic forum for researchers and practitioners to present recent advances, innovative methodologies, and practical experiences related to federated learning and its applications. This Special Issue will, thus, bridge the gap between theoretical research and real-world deployment by encouraging contributions that jointly consider algorithm design, system architecture, and application requirements. The topics covered in this Special Issue closely align with the scope of the journal, particularly in areas related to distributed systems, edge and mobile computing, intelligent electronic systems, communication-efficient learning, and privacy-aware technologies. By focusing on federated learning as a key enabling technology for next-generation intelligent systems, this Special Issue will contribute to the advancement of secure, efficient, and scalable machine learning solutions in modern electronic and computing environments.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

• Federated learning algorithms and theoretical foundations;
• Communication-efficient and resource-aware federated learning methods;
• Privacy-preserving, secure, and trustworthy federated learning;
• Personalized and adaptive federated learning models;
• Federated learning for edge computing and mobile environments;
• Federated learning under non-independent and non-identically distributed data;
• Performance guarantees and robustness of federated learning with low-quality or noisy data;
• System architectures and implementations of federated learning;
• Practical applications and case studies of federated learning in real-world scenarios.

We look forward to receiving your contributions.

Dr. Pengfei Wang
Guest Editor

Mr. Zhenwei Wang
Guest Editor Assistant
Email: zhenweiwang@mail.dlut.edu.cn
Affiliation: School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• federated learning
• distributed machine learning
• privacy preservation
• edge computing
• communication-efficient learning
• non-independent and identically distributed data
• system heterogeneity
• real-world applications and system implementation