Distributed Active Learning Strategies on Edge Computing

Jia Qian; Sarada Prasad Gochhayat; Lars Kai Hansen

doi:10.1109/CSCloud/EdgeCom.2019.00029

Distributed Active Learning Strategies on Edge Computing

Jia Qian, Sarada Prasad Gochhayat, Lars Kai Hansen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Fog platform brings the computing power from the remote cloud-side closer to the edge devices to reduce latency, as the unprecedented generation of data causes ineligible latency to process the data in a centralized fashion at the Cloud. In this new setting, edge devices with distributed computing capability, such as sensors, surveillance camera, can communicate with fog nodes with less latency. Furthermore, local computing (at edge side) may improve privacy and trust. In this paper, we present a new method, in which, we decompose the data processing, by dividing them between edge devices and fog nodes, intelligently. We apply active learning on edge devices; and federated learning on the fog node which significantly reduces the data samples to train the model as well as the communication cost. To show the effectiveness of the proposed method, we implemented and evaluated its performance on a benchmark images data set.

Original language	English
Title of host publication	Proceedings of 6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud
Editors	Meikang Qiu
Publisher	IEEE
Publication date	1 Jun 2019
Pages	221-226
Article number	8854053
ISBN (Electronic)	9781728116600
DOIs	https://doi.org/10.1109/CSCloud/EdgeCom.2019.00029
Publication status	Published - 1 Jun 2019
Event	6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud/EdgeCom 2019 - Paris, France Duration: 21 Jun 2019 → 23 Jun 2019

Conference

Conference	6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud/EdgeCom 2019
Country	France
City	Paris
Period	21/06/2019 → 23/06/2019
Sponsor	IEEE, IEEE, IEEE, IEEE, Columbia University

Keywords

Active Learning
Bayesian Neural Network
Edge Computing
Federated Learning
Fog Computing

Access to Document

10.1109/CSCloud/EdgeCom.2019.00029

Fingerprint Dive into the research topics of 'Distributed Active Learning Strategies on Edge Computing'. Together they form a unique fingerprint.

Cite this

Qian, J., Gochhayat, S. P., & Hansen, L. K. (2019). Distributed Active Learning Strategies on Edge Computing. In M. Qiu (Ed.), Proceedings of 6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud (pp. 221-226). [8854053] IEEE. https://doi.org/10.1109/CSCloud/EdgeCom.2019.00029

@inproceedings{33ad8a9968ac490ab6692dd8c6aab301,

title = "Distributed Active Learning Strategies on Edge Computing",

abstract = "Fog platform brings the computing power from the remote cloud-side closer to the edge devices to reduce latency, as the unprecedented generation of data causes ineligible latency to process the data in a centralized fashion at the Cloud. In this new setting, edge devices with distributed computing capability, such as sensors, surveillance camera, can communicate with fog nodes with less latency. Furthermore, local computing (at edge side) may improve privacy and trust. In this paper, we present a new method, in which, we decompose the data processing, by dividing them between edge devices and fog nodes, intelligently. We apply active learning on edge devices; and federated learning on the fog node which significantly reduces the data samples to train the model as well as the communication cost. To show the effectiveness of the proposed method, we implemented and evaluated its performance on a benchmark images data set.",

keywords = "Active Learning, Bayesian Neural Network, Edge Computing, Federated Learning, Fog Computing",

author = "Jia Qian and Gochhayat, {Sarada Prasad} and Hansen, {Lars Kai}",

year = "2019",

month = jun,

day = "1",

doi = "10.1109/CSCloud/EdgeCom.2019.00029",

language = "English",

pages = "221--226",

editor = "Meikang Qiu",

booktitle = "Proceedings of 6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud",

publisher = "IEEE",

address = "United States",

note = "6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud/EdgeCom 2019 ; Conference date: 21-06-2019 Through 23-06-2019",

}

Qian, J, Gochhayat, SP & Hansen, LK 2019, Distributed Active Learning Strategies on Edge Computing. in M Qiu (ed.), Proceedings of 6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud., 8854053, IEEE, pp. 221-226, 6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud/EdgeCom 2019, Paris, France, 21/06/2019. https://doi.org/10.1109/CSCloud/EdgeCom.2019.00029

Distributed Active Learning Strategies on Edge Computing. / Qian, Jia; Gochhayat, Sarada Prasad; Hansen, Lars Kai.

Proceedings of 6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud. ed. / Meikang Qiu. IEEE, 2019. p. 221-226 8854053.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Distributed Active Learning Strategies on Edge Computing

AU - Qian, Jia

AU - Gochhayat, Sarada Prasad

AU - Hansen, Lars Kai

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Fog platform brings the computing power from the remote cloud-side closer to the edge devices to reduce latency, as the unprecedented generation of data causes ineligible latency to process the data in a centralized fashion at the Cloud. In this new setting, edge devices with distributed computing capability, such as sensors, surveillance camera, can communicate with fog nodes with less latency. Furthermore, local computing (at edge side) may improve privacy and trust. In this paper, we present a new method, in which, we decompose the data processing, by dividing them between edge devices and fog nodes, intelligently. We apply active learning on edge devices; and federated learning on the fog node which significantly reduces the data samples to train the model as well as the communication cost. To show the effectiveness of the proposed method, we implemented and evaluated its performance on a benchmark images data set.

AB - Fog platform brings the computing power from the remote cloud-side closer to the edge devices to reduce latency, as the unprecedented generation of data causes ineligible latency to process the data in a centralized fashion at the Cloud. In this new setting, edge devices with distributed computing capability, such as sensors, surveillance camera, can communicate with fog nodes with less latency. Furthermore, local computing (at edge side) may improve privacy and trust. In this paper, we present a new method, in which, we decompose the data processing, by dividing them between edge devices and fog nodes, intelligently. We apply active learning on edge devices; and federated learning on the fog node which significantly reduces the data samples to train the model as well as the communication cost. To show the effectiveness of the proposed method, we implemented and evaluated its performance on a benchmark images data set.

KW - Active Learning

KW - Bayesian Neural Network

KW - Edge Computing

KW - Federated Learning

KW - Fog Computing

U2 - 10.1109/CSCloud/EdgeCom.2019.00029

DO - 10.1109/CSCloud/EdgeCom.2019.00029

M3 - Article in proceedings

SP - 221

EP - 226

BT - Proceedings of 6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud

A2 - Qiu, Meikang

PB - IEEE

T2 - 6th IEEE International Conference on Cyber Security and Cloud Computing and 5th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud/EdgeCom 2019

Y2 - 21 June 2019 through 23 June 2019

ER -