King's College London

Research portal

Wireless Data Acquisition for Edge Learning: Importance-Aware Retransmission

Research output: Chapter in Book/Report/Conference proceedingConference paper

Standard

Wireless Data Acquisition for Edge Learning : Importance-Aware Retransmission. / Liu, Dongzhu; Zhu, Guangxu; Zhang, Jun; Huang, Kaibin.

2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). IEEE Press, 2019. p. 1-5.

Research output: Chapter in Book/Report/Conference proceedingConference paper

Harvard

Liu, D, Zhu, G, Zhang, J & Huang, K 2019, Wireless Data Acquisition for Edge Learning: Importance-Aware Retransmission. in 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). IEEE Press, pp. 1-5. https://doi.org/10.1109/SPAWC.2019.8815498

APA

Liu, D., Zhu, G., Zhang, J., & Huang, K. (2019). Wireless Data Acquisition for Edge Learning: Importance-Aware Retransmission. In 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) (pp. 1-5). IEEE Press. https://doi.org/10.1109/SPAWC.2019.8815498

Vancouver

Liu D, Zhu G, Zhang J, Huang K. Wireless Data Acquisition for Edge Learning: Importance-Aware Retransmission. In 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). IEEE Press. 2019. p. 1-5 https://doi.org/10.1109/SPAWC.2019.8815498

Author

Liu, Dongzhu ; Zhu, Guangxu ; Zhang, Jun ; Huang, Kaibin. / Wireless Data Acquisition for Edge Learning : Importance-Aware Retransmission. 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). IEEE Press, 2019. pp. 1-5

Bibtex Download

@inbook{0e53ae126d7a4e4fb4b636d76b4eaef6,
title = "Wireless Data Acquisition for Edge Learning: Importance-Aware Retransmission",
abstract = "By deploying machine learning algorithms at the network edge, edge learning recently emerges as a promising framework to support intelligent mobile services. It effectively leverages the rich data collected by abundant mobile devices, and exploits the proximate edge computing resource for low-latency execution. Edge learning crosses two disciplines, machine learning and wireless communication, and thereby gives rise to many new research issues. In this paper, we address a wireless data acquisition problem, which involves a retransmission decision in each communication round to optimize the data quality-vs-quantity tradeoff. A new retransmission protocol called importance-aware automatic-repeat-request (importance ARQ) is proposed. Unlike classic ARQ focusing merely on reliability, importance ARQ selectively retransmits a data sample based on its uncertainty that can be measured using the model under training. Underpinning the proposed protocol is an elegant communication-learning relation between two corresponding metrics, i.e., signal-to-noise ratio (SNR) and data uncertainty. This new relation facilitates the design of a simple threshold based policy for retransmission decisions. As demonstrated via experiments with real datasets, the proposed method avoids learning performance degradation caused by channel noise while achieving faster convergence than conventional SNR-based ARQ.",
author = "Dongzhu Liu and Guangxu Zhu and Jun Zhang and Kaibin Huang",
year = "2019",
doi = "10.1109/SPAWC.2019.8815498",
language = "Undefined/Unknown",
pages = "1--5",
booktitle = "2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)",
publisher = "IEEE Press",

}

RIS (suitable for import to EndNote) Download

TY - CHAP

T1 - Wireless Data Acquisition for Edge Learning

T2 - Importance-Aware Retransmission

AU - Liu, Dongzhu

AU - Zhu, Guangxu

AU - Zhang, Jun

AU - Huang, Kaibin

PY - 2019

Y1 - 2019

N2 - By deploying machine learning algorithms at the network edge, edge learning recently emerges as a promising framework to support intelligent mobile services. It effectively leverages the rich data collected by abundant mobile devices, and exploits the proximate edge computing resource for low-latency execution. Edge learning crosses two disciplines, machine learning and wireless communication, and thereby gives rise to many new research issues. In this paper, we address a wireless data acquisition problem, which involves a retransmission decision in each communication round to optimize the data quality-vs-quantity tradeoff. A new retransmission protocol called importance-aware automatic-repeat-request (importance ARQ) is proposed. Unlike classic ARQ focusing merely on reliability, importance ARQ selectively retransmits a data sample based on its uncertainty that can be measured using the model under training. Underpinning the proposed protocol is an elegant communication-learning relation between two corresponding metrics, i.e., signal-to-noise ratio (SNR) and data uncertainty. This new relation facilitates the design of a simple threshold based policy for retransmission decisions. As demonstrated via experiments with real datasets, the proposed method avoids learning performance degradation caused by channel noise while achieving faster convergence than conventional SNR-based ARQ.

AB - By deploying machine learning algorithms at the network edge, edge learning recently emerges as a promising framework to support intelligent mobile services. It effectively leverages the rich data collected by abundant mobile devices, and exploits the proximate edge computing resource for low-latency execution. Edge learning crosses two disciplines, machine learning and wireless communication, and thereby gives rise to many new research issues. In this paper, we address a wireless data acquisition problem, which involves a retransmission decision in each communication round to optimize the data quality-vs-quantity tradeoff. A new retransmission protocol called importance-aware automatic-repeat-request (importance ARQ) is proposed. Unlike classic ARQ focusing merely on reliability, importance ARQ selectively retransmits a data sample based on its uncertainty that can be measured using the model under training. Underpinning the proposed protocol is an elegant communication-learning relation between two corresponding metrics, i.e., signal-to-noise ratio (SNR) and data uncertainty. This new relation facilitates the design of a simple threshold based policy for retransmission decisions. As demonstrated via experiments with real datasets, the proposed method avoids learning performance degradation caused by channel noise while achieving faster convergence than conventional SNR-based ARQ.

U2 - 10.1109/SPAWC.2019.8815498

DO - 10.1109/SPAWC.2019.8815498

M3 - Conference paper

SP - 1

EP - 5

BT - 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)

PB - IEEE Press

ER -

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454