Title
Wireless Data Acquisition for Edge Learning: Data-Importance Aware Retransmission
Abstract
By deploying machine-learning algorithms at the network edge, edge learning can leverage the enormous real-time data generated by billions of mobile devices to train AI models, which enable intelligent mobile applications. In this emerging research area, one key direction is to efficiently utilize radio resources for wireless data acquisition to minimize the latency of executing a learning task at an edge server. Along this direction, we consider the specific problem of retransmission decision in each communication round to ensure both reliability and quantity of those training data for accelerating model convergence. To solve the problem, a new retransmission protocol called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">data-importance aware automatic-repeat-request</i> (importance ARQ) is proposed. Unlike the classic ARQ focusing merely on reliability, importance ARQ selectively retransmits a data sample based on its <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">uncertainty</i> which helps learning and can be measured using the model under training. Underpinning the proposed protocol is a derived elegant communication-learning relation between two corresponding metrics, i.e., <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">signal-to-noise ratio</i> (SNR) and data uncertainty. This relation facilitates the design of a simple threshold based policy for importance ARQ. The policy is first derived based on the classic classifier model of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">support vector machine</i> (SVM), where the uncertainty of a data sample is measured by its distance to the decision boundary. The policy is then extended to the more complex model of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">convolutional neural networks</i> (CNN) where data uncertainty is measured by entropy. Extensive experiments have been conducted for both the SVM and CNN using real datasets with balanced and imbalanced distributions. Experimental results demonstrate that importance ARQ effectively copes with channel fading and noise in wireless data acquisition to achieve faster model convergence than the conventional channel-aware ARQ. The gain is more significant when the dataset is imbalanced.
Year
DOI
Venue
2021
10.1109/TWC.2020.3024980
IEEE Transactions on Wireless Communications
Keywords
DocType
Volume
Retransmission,resource management,data acquisition,edge machine learning
Journal
20
Issue
ISSN
Citations 
1
1536-1276
5
PageRank 
References 
Authors
0.44
0
5
Name
Order
Citations
PageRank
Dongzhu Liu1252.53
Guangxu Zhu234324.03
Qunsong Zeng3121.57
Jun Zhang43772190.36
Kaibin Huang53155182.06