Name
Title | ||
|---|---|---|
Data-Importance Aware User Scheduling for Communication-Efficient Edge Machine Learning |
Abstract | ||
|---|---|---|
With the prevalence of intelligent mobile applications, edge learning is emerging as a promising technology for powering fast intelligence acquisition for edge devices from distributed data generated at the network edge. One critical task of edge learning is to efficiently utilize the limited radio resource to acquire data samples for model training at an edge server. In this paper, we develop a novel user scheduling algorithm for data acquisition in edge learning, called
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">(data) importance-aware scheduling</i>
. A key feature of this scheduling algorithm is that it takes into account the informativeness of data samples, besides communication reliability. Specifically, the scheduling decision is based on a
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">data importance indicator</i>
(DII), elegantly incorporating two “important” metrics from communication and learning perspectives, i.e., the
<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
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">data uncertainty</i>
. We first derive an explicit expression for this indicator targeting the classic classifier 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. Then, the result is extended to
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">convolutional neural networks</i>
(CNN) by replacing the distance based uncertainty measure with the entropy. As demonstrated via experiments using real datasets, the proposed importance-aware scheduling can exploit the two-fold multi-user diversity, namely the diversity in both the multiuser channels and the distributed data samples. This leads to faster model convergence than the conventional scheduling schemes that exploit only a single type of diversity. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/TCCN.2020.2999606 | IEEE Transactions on Cognitive Communications and Networking |
Keywords | DocType | Volume |
Scheduling,resource management,image classification,multiuser channels,data acquisition | Journal | 7 |
Issue | ISSN | Citations |
1 | 2332-7731 | 4 |
PageRank | References | Authors |
0.42 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dongzhu Liu | 1 | 25 | 2.53 |
| Guangxu Zhu | 2 | 343 | 24.03 |
| Jun Zhang | 3 | 3772 | 190.36 |
| Kaibin Huang | 4 | 3155 | 182.06 |