Federated Neural Networks: Design and Deployment
A special issue of Future Internet (ISSN 1999-5903). This special issue belongs to the section "Big Data and Augmented Intelligence".
Deadline for manuscript submissions: 1 November 2026 | Viewed by 149
Special Issue Editors
Interests: federated learning; data privacy and security
2. Faculty of Engineering & Information Technology, University of Technology Sydney (UTS), 15 Broadway, Ultimo, NSW 2007, Australia
Interests: federated learning; machine learning
Special Issue Information
Dear Colleagues,
Federated Learning (FL) has emerged as a transformative paradigm for training machine learning models across distributed data sources while preserving data privacy and ownership. It has become particularly relevant in privacy-sensitive domains such as healthcare, finance, telecommunications, and smart infrastructure, as it enables collaborative learning without direct data sharing. Recent advances have further integrated deep and neural network-based models into federated settings, giving rise to federated neural networks (FNNs) that combine representational power with distributed intelligence. Beyond privacy preservation, federated approaches offer improved scalability, robustness, and efficient utilization of decentralized computational resources.
Despite their potential, the design and deployment of federated neural networks present significant challenges. These include heterogeneous and non-IID data distributions, mixed horizontal and vertical partitioning, communication efficiency, system heterogeneity, model convergence, robustness to unreliable clients, and security threats. Moreover, deploying federated neural networks in real-world environments requires careful consideration of system architecture, synchronization strategies, resource constraints and regulatory compliance.
This Special Issue aims to advance the state of the art in federated neural networks by bringing together theoretical foundations, algorithmic innovations, and real-world deployment studies. We welcome original contributions that explore novel federated neural architectures, optimization and communication strategies, privacy and security mechanisms, and practical applications across diverse domains. Through this Special Issue, we seek to bridge the gap between federated learning theory and scalable, deployable neural network systems for the future internet.
Dr. Amir Anees
Dr. Gnana K. Bharathy
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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Future Internet is an international peer-reviewed open access monthly 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 1800 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
- federated learning
- federated neural networks
- privacy-preserving machine learning
- distributed deep learning
- non-IID data and data heterogeneity
- communication-efficient learning
- secure and robust federated systems
- model deployment and scalability
- healthcare and industrial applications
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.
