Decentralized Intelligence for the Future Internet: Federated Learning, Edge AI, and Beyond
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 March 2027 | Viewed by 44
Special Issue Editors
Interests: AIoT; federated learning; on-device AI
Interests: federated learning; deep learning; intelligent systems
Interests: applied machine learning; federated learning; multi-agent intelligence
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Modern IoT ecosystems generate massive volumes of data across millions of distributed devices. At the same time, transmitting this data to centralized cloud servers for training is increasingly impractical due to privacy concerns, bandwidth limitations, and latency requirements. Federated learning, split learning, and other decentralized paradigms have emerged as promising solutions, enabling collaborative model training across distributed devices while preserving data privacy and reducing communication overhead. Meanwhile, advances in on-device AI and neural architecture search are pushing the boundaries of what resource-constrained devices can achieve independently.
However, significant challenges remain. Heterogeneous device capabilities, non-IID data distributions, limited bandwidth, and security vulnerabilities all complicate the deployment of decentralized intelligence in real-world IoT environments. Bridging the gap between theoretical frameworks and practical deployment on edge devices requires innovation across model compression, adaptive inference, topology optimization, and privacy-preserving computation.
This Special Issue invites original research and review articles exploring the design, optimization, and deployment of decentralized and federated learning systems for next-generation IoT and edge networks. Both theoretical contributions and practical system implementations are welcome.
Topics of interest include, but are not limited to, the following:
- Federated and split learning frameworks for edge and IoT systems;
- Neural architecture search for resource-constrained devices;
- Communication-efficient and bandwidth-aware distributed training;
- Privacy, security, and robustness in decentralized learning;
- On-device AI and adaptive inference strategies;
- Topology optimization for decentralized learning networks;
- Multi-modal and cross-device federated learning;
- AI-driven network management and optimization;
- Personalization and fairness in federated systems;
- Real-world deployment and benchmarking of edge AI systems.
Dr. Atif Rizwan
Dr. Rashid Ahmad
Dr. Anam Nawaz Khan
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
- split learning
- edge AI
- internet of things (IoT)
- on-device intelligence
- neural architecture search
- decentralized learning
- privacy-preserving machine learning
- communication-efficient training
- resource-constrained computing
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.
