Special Issue "Federated Learning for Internet of Things"

Dear Colleagues,

With the prevalence of IoT technologies and artificial intelligence (AI), new computing paradigms, systems and applications have been introduced, such as real-time surveillance, personalized healthcare, precision agriculture, automated manufacturing, etc. Meanwhile, new challenges have also emerged due to the increasing concerns regarding the privacy and security of large-scale IoT systems. In many IoT applications (healthcare, surveillance, etc.), data generated from sensors and actuators are owned by individuals or private sector entities, who are reluctant to share their data for AI models due to privacy concerns.

Federated learning (FL) has great potential to enable AI in privacy-sensitive IoT systems, where data generated at the client-side devices can be processed and trained at a local level and synthesized by AI models deployed at the server side. In contrast to traditional AI techniques collecting data in a central place for training AI, FL sends AI to the proximity of end users (i.e., data owners), thus addressing data privacy and security in IoT systems. However, there are still many significant gaps and technical challenges in applying FL in large-scale IoT systems that enable robust, real-time, secure IoT data analytics.

The aim of this Special Issue is to bring together researchers in the field of IoT, AI, machine learning, and networks to address new challenges in FL for IoT systems by soliciting original, previously unpublished empirical, experimental, and theoretical research works at the intersection of these technologies. Potential topics include (but are not limited to):

• FL in IoT;
• Deep learning in IoT;
• Security and privacy schemes for FL in IoT;
• Design, validation and optimization of FL in IoT;
• Efficient networking and communication of FL in IoT
• AI and machine learning in multi-agent systems;
• Efficient privacy-preserving AI and machine learning;
• Homomorphic encryption for FL in IoT;
• Lightweight and producible FL and AI models in IoT.

Dr. Bo Yuan
Dr. Leonardo Stella
Dr. Muhammad Kazim
Prof. Dr. Rongbo Zhu
Prof. Dr. Jinfu Chen
Prof. Dr. Lu Liu
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. Journal of Sensor and Actuator Networks 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 1600 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
• IoT
• AI
• sensors
• security
• privacy
• encryption