Data-Driven Decentralized Learning for Future Communication Networks

Dear Colleagues,

In recent years, academia and industry have witnessed the prosperity and development of artificial intelligence technology, and, more noticeably, various intelligent applications are increasingly sinking to the edge close to users. In this regard, data-driven decentralized learning technology based on cloud–edge collaboration has received widespread attention. Decentralized learning in the context of cloud–edge collaboration is a new architecture combining cloud computing and edge computing with the help of networks. It utilizes the mighty computing power and storage capacity of cloud computing, along with the low latency, high reliability, and flexibility of edge computing to achieve better computing performance and user experience. This collaboration processes data and tasks jointly between the cloud and the edge. Edge devices can collect and process data through sensors and other devices and then delegate some tasks requiring more substantial computing power to the cloud for processing. Simultaneously, the cloud can reduce its workload and improve response speed by delegating some data and tasks to edge devices. This technology can enhance computing efficiency and reliability, improving users' experience. It has become the key to supporting the realization of 6G edge intelligence. Cloud–edge collaboration not only offers strong support for edge networking, resource allocation, and network optimization (AI for edge), it also provides computing services and collaborative intelligence and reduces latency to meet the real-time business needs of the network (AI on edge).

This Special Issue aims to collect new innovative ideas to apply data-driven decentralized learning models and algorithms for future communication networks. Both primarily theoretical deduction and applied decentralized learning technologies based on mathematical ideas are welcomed in this Special Issue.

Dr. Chuanting Zhang
Dr. Shuping Dang
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.

• decentralized learning for wireless communications
• cloud–edge–deivce collaborative learning
• wireless traffic analysis and resource management
• intelligent communications
• large language models and their application in communication networks