Data-Importance Aware Radio Resource Allocation: Wireless Communication Helps Machine Learning

TL;DR

This paper introduces data-importance aware radio resource allocation schemes for edge AI, prioritizing data based on its impact on machine learning performance to optimize wireless resource utilization.

Contribution

It proposes two importance criteria for data in centralized and distributed edge machine learning, along with corresponding resource allocation schemes.

Findings

Improved machine learning performance with importance-aware allocation

Effective differentiation of data importance based on ML impact

Extensive experiments verify scheme effectiveness

Abstract

The rich mobile data and edge computing enabled wireless networks motivate to deploy artificial intelligence (AI) at network edge, known as \emph{edge AI}, which integrates wireless communication and machine learning. In communication, data bits are equally important, while in machine learning some data bits are more important. Therefore we can allocate more radio resources to the more important data and allocate less radio resources to the less important data, so as to efficiently utilize the limited radio resources. To this end, how to define "more or less important" of data is the key problem. In this article, we propose two importance criteria to differentiate data's importance based on their effects on machine learning, one for centralized edge machine learning and the other for distributed edge machine learning. Then, the corresponding radio resource allocation schemes are proposed to improve performance of machine learning. Extensive experiments are conducted for verifying the effectiveness of the proposed data-importance aware radio resource allocation schemes.