New Trends in Transfer Learning and Federated Learning
A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".
Deadline for manuscript submissions: 15 December 2025 | Viewed by 13
Special Issue Editors
Interests: federated learning; cyber-physical systems; software engineering; trustworthy AI
Special Issue Information
Dear Colleagues,
With the rapid advancement of artificial intelligence and the growing demand for privacy-aware, efficient machine learning systems, Transfer Learning (TL) and Federated Learning (FL) have emerged as transformative technologies in modern AI. Transfer Learning enables the reuse of knowledge across different domains, accelerating learning processes, while federated learning facilitates decentralized model training, allowing sensitive data to remain local. When combined, these approaches offer promising solutions to challenges in data efficiency, privacy protection, and distributed computation.
The integration of TL and FL presents both tremendous opportunities and significant challenges. Applications include personalized healthcare, intelligent edge devices, cross-domain recommendation systems, and more. Nevertheless, several critical issues remain to be addressed—including model generalization across domains, communication efficiency in federated settings, privacy guarantees, and handling heterogeneous data in decentralized settings.
This Special Issue seeks high-quality submissions that present recent advances, address existing challenges, and explore new opportunities in transfer learning and federated learning. We welcome both original research articles and comprehensive reviews that advance theoretical foundations or demonstrate impactful applications.
Research areas of interest include, (but are not limited to, the following topics:
- Federated learning and transfer learning algorithms and architectures;
- Federated learning optimization techniques;
- Federated transfer learning approaches;
- Privacy-preserving mechanisms in transfer and federated learning;
- Cross-domain adaptation methods;
- Communication- and memory-efficient federated learning;
- Handling non-IID data in federated learning;
- Robustness and security in transfer learning and federated learning systems;
- Applications in healthcare, IoT, finance, and other domains;
Theoretical foundations of transfer and federated learning.
Dr. Ming Hu
Dr. Yangguang Cui
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. 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.
Keywords
- transfer learning
- federated learning
- domain adaptation
- privacy-preserving machine learning
- decentralized learning
- heterogeneous data
- federated transfer learning
- communication-efficient learning
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
