Federated Learning Strategies for Machine Learning

Dear Colleagues,

Federated learning introduces new perspectives in machine learning by enabling model training across decentralised devices. Participants only share the model updates without exchanging local data samples in full compliance with the General Data Protection Regulation. This approach offers many advantages for large-scale applications, from preserving data privacy to providing faster training and effective learning transfer among models exposed to data collected in different environments.

Advanced techniques are still needed to integrate this paradigm into real-world scenarios and effectively address communication overhead issues, privacy and security vulnerabilities, the lack of standardisation, and model aggregation for non-independent and identically distributed data.

In this Special Issue, original articles and reviews related to (but not limited to) the following topics are welcome:

1. Federated learning algorithms;
2. Federated reinforcement learning;
3. Federated generative model;
4. Privacy and security in federated learning;
5. Communication efficiency for federated learning;
6. Federated learning frameworks;
7. Standardisation and interoperability;
8. Transfer of learning;
9. Multi-task learning;
10. Domain adaptation;
11. Evaluation metrics in transfer learning;
12. Online and incremental model aggregation;
13. Model and data fusion;
14. Interpretability in aggregated models;
15. Ensemble learning;
16. Advanced learning algorithms;
17. Distributed learning algorithms;
18. Scalability and performance in distributed learning;
19. Real-world machine learning applications with data privacy constraints;
20. Federated learning applications.

We look forward to receiving your contributions.

Dr. Lavinia Ferariu
Prof. Dr. Constantin Florin Caruntu
Dr. Carlos Pascal
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 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 algorithms
• federated reinforcement learning
• federated generative model
• privacy and security in federated learning
• communication efficiency for federated learning
• federated learning frameworks
• standardisation and interoperability
• multi-task learning
• evaluation metrics in transfer learning
• advanced learning algorithms
• distributed learning algorithms
• scalability and performance in distributed learning
• real-world machine learning applications with data privacy constraints