Federated Learning: Methods, Challenges and Applications

Dear Colleagues,

Federated learning enables multiple participants to train a shared model without directly exchanging their local data. It has attracted considerable interest in distributed machine learning, privacy protection, edge computing and wireless networks. However, its practical deployment still faces several fundamental challenges. These include non-independent and identically distributed data, heterogeneous devices and networks, limited communication and computing resources, unreliable client participation, privacy leakage, security attacks and the need for fair and personalized learning.

This Special Issue, entitled “Federated Learning: Methods, Challenges and Applications,” aims to present recent theoretical and practical advances in federated learning and to promote its development from algorithm design to real-world implementation. We invite original research articles and review papers on topics including, but not limited to, federated optimization and convergence analysis; client selection and resource allocation; communication- and energy-efficient learning; asynchronous, hierarchical, decentralized and personalized federated learning; privacy-preserving mechanisms and secure aggregation; robustness against poisoning, backdoor and Byzantine attacks; incentive design, fairness and model evaluation and the integration of federated learning with edge computing, wireless communications and distributed systems.

Application-oriented studies are also encouraged, particularly in mobile and wireless networks, the Internet of Things, healthcare, industrial systems, autonomous systems, smart cities, finance and recommendation services. Contributions involving practical implementations, experimental results, testbeds, datasets and case studies are especially welcome.

Existing studies often address learning algorithms, communication efficiency, privacy, security or applications separately. This Special Issue seeks to supplement the existing literature by examining these issues in a unified manner and by clarifying the trade-offs among learning performance, communication overhead, energy consumption, privacy, robustness and system scalability. It will provide a focused forum for researchers and practitioners to report new methods, identify open challenges and share practical experience in the design and deployment of federated learning systems. The issue also welcomes studies that support reproducible evaluation, interoperable platforms and future standardization.

Dr. Wanli Ni
Dr. Fangfang Yin
Dr. Weikun Kong
Guest Editors

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-anonymized 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-preserving learning
• communication-efficient learning
• personalized federated learning
• edge intelligence
• security and robustness
• Internet of Things