Abstract
As a large amount of real-time data generated by billions of mobile devices nowadays, how to efficiently upload and process these data to server to realize ubiquitous intelligence at network edge is critical. A key challenge is to use limited radio resources to transmit massive data samples. Motivated by active learning, a communication-efficient way is to select most informative data samples for model training. In this article, we develop a new data scheduling scheme based on data representation. Specifically, the devices would like to transmit the most representative data samples, while the server prefers to schedule the least representative ones. A scheduling scheme is designed for such value asymmetry of data samples. The experimental results demonstrate that the proposed scheme can significantly improve the performance of machine learning.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
