Federated Learning and Edge Intelligence: Mathematical Models, Algorithms, and Applications

Dear Colleagues,

We are pleased to invite contributions to our upcoming Special Issue of Mathematics, entitled "Federated Learning and Edge Intelligence: Mathematical Models, Algorithms, and Applications”. This Special Issue aims to delve into the application of Federated Learning (FL) and Edge Intelligence (EI) on resource-constrained devices, a field that not only faces unique challenges but also offers groundbreaking opportunities at the forefront of modern artificial intelligence research. The importance of this research area lies in its potential to drive profound transformations across multiple domains, from the Internet of Things to mobile computing, reflecting the evolving complexity of data processing and computation in today’s world.

The goal of this Special Issue is to explore both the theoretical foundations of FL and EI in resource-constrained environments and their practical implementations, while advancing the journal’s commitment to publishing significant technological breakthroughs. Our objective is to gather research that showcases innovative mathematical models, algorithms, and applications relevant to FL and EI on resource-constrained devices. These contributions will provide a comprehensive perspective on the mathematical challenges and solutions within these interconnected fields. If successful, this Special Issue will not only serve as an important platform for academic exchange but also has the potential to be published in book form, becoming an authoritative reference in the field.

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

• Optimization of federated learning algorithms in resource-constrained environments;
• Privacy-preserving mechanisms in edge intelligence;
• Strategies for improving communication efficiency;
• Case studies of real-world FL application scenarios;
• Model compression and acceleration methods;
• Architectural design of federated learning systems;
• Methods for tackling heterogeneous problem in Federated Learning;
• Applications of Federated Learning, e.g., Federated Recommendation.

I look forward to receiving your contributions.

Dr. Haozhao Wang
Guest Editor

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 100 words) can be sent to the Editorial Office for announcement on this website.

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. Mathematics 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 2600 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
• edge learning
• heterogeneity
• resource-constrained