Finding critical edges in networks through deep reinforcement learning

Xuecheng Wang; Chen Zeng; Lu Han; Xi Zeng; Junxia Wang; Wei Luo; Bei Jiang; Jiajie Peng

doi:10.1109/ICICN59530.2023.10393114

Finding critical edges in networks through deep reinforcement learning

Xuecheng Wang, Chen Zeng, Lu Han, Xi Zeng, Junxia Wang, Wei Luo, Bei Jiang, Jiajie Peng

School of Computer Science

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

Abstract

The network is a powerful tool to study the interaction of system units, and the edge is an important part of the network as it represents relationships between nodes. Critical edges play an irreplaceable role in information transmission between nodes and maintaining network connectivity and integrity. Therefore, the identification of critical edges in networks is an indispensable part of network analysis, which has great practical significance. Here, we propose an algorithm IKEoN. Based on the Deep Q-learning algorithm, this algorithm identify the critical edges in the network. Instead of using labeled data sets, IKEoN uses the constant interaction between agents and the environment to train the model, which reduces the influence of network noise and improves the recognition performance. The experimental results show that the proposed method outperforms the existing methods.

Original language	English
Title of host publication	ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	693-701
Number of pages	9
ISBN (Electronic)	9798350314014
DOIs	https://doi.org/10.1109/ICICN59530.2023.10393114
State	Published - 2023
Event	2023 IEEE 11th International Conference on Information, Communication and Networks, ICICN 2023 - Hybrid, Xi'an, China Duration: 17 Aug 2023 → 20 Aug 2023

Publication series

Name	ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks

Conference

Conference	2023 IEEE 11th International Conference on Information, Communication and Networks, ICICN 2023
Country/Territory	China
City	Hybrid, Xi'an
Period	17/08/23 → 20/08/23

Keywords

critical edges
deep reinforcement learning
network

Access to Document

10.1109/ICICN59530.2023.10393114

Cite this

Wang, X., Zeng, C., Han, L., Zeng, X., Wang, J., Luo, W., Jiang, B., & Peng, J. (2023). Finding critical edges in networks through deep reinforcement learning. In ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks (pp. 693-701). (ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICICN59530.2023.10393114

Wang, Xuecheng ; Zeng, Chen ; Han, Lu et al. / Finding critical edges in networks through deep reinforcement learning. ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 693-701 (ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks).

@inproceedings{b2d39c64d95b4123ba33908855b3397c,

title = "Finding critical edges in networks through deep reinforcement learning",

abstract = "The network is a powerful tool to study the interaction of system units, and the edge is an important part of the network as it represents relationships between nodes. Critical edges play an irreplaceable role in information transmission between nodes and maintaining network connectivity and integrity. Therefore, the identification of critical edges in networks is an indispensable part of network analysis, which has great practical significance. Here, we propose an algorithm IKEoN. Based on the Deep Q-learning algorithm, this algorithm identify the critical edges in the network. Instead of using labeled data sets, IKEoN uses the constant interaction between agents and the environment to train the model, which reduces the influence of network noise and improves the recognition performance. The experimental results show that the proposed method outperforms the existing methods.",

keywords = "critical edges, deep reinforcement learning, network",

author = "Xuecheng Wang and Chen Zeng and Lu Han and Xi Zeng and Junxia Wang and Wei Luo and Bei Jiang and Jiajie Peng",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE 11th International Conference on Information, Communication and Networks, ICICN 2023 ; Conference date: 17-08-2023 Through 20-08-2023",

year = "2023",

doi = "10.1109/ICICN59530.2023.10393114",

language = "英语",

series = "ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "693--701",

booktitle = "ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks",

}

Wang, X, Zeng, C, Han, L, Zeng, X, Wang, J, Luo, W, Jiang, B & Peng, J 2023, Finding critical edges in networks through deep reinforcement learning. in ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks. ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks, Institute of Electrical and Electronics Engineers Inc., pp. 693-701, 2023 IEEE 11th International Conference on Information, Communication and Networks, ICICN 2023, Hybrid, Xi'an, China, 17/08/23. https://doi.org/10.1109/ICICN59530.2023.10393114

Finding critical edges in networks through deep reinforcement learning. / Wang, Xuecheng; Zeng, Chen; Han, Lu et al.
ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks. Institute of Electrical and Electronics Engineers Inc., 2023. p. 693-701 (ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks).

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

TY - GEN

T1 - Finding critical edges in networks through deep reinforcement learning

AU - Wang, Xuecheng

AU - Zeng, Chen

AU - Han, Lu

AU - Zeng, Xi

AU - Wang, Junxia

AU - Luo, Wei

AU - Jiang, Bei

AU - Peng, Jiajie

PY - 2023

Y1 - 2023

N2 - The network is a powerful tool to study the interaction of system units, and the edge is an important part of the network as it represents relationships between nodes. Critical edges play an irreplaceable role in information transmission between nodes and maintaining network connectivity and integrity. Therefore, the identification of critical edges in networks is an indispensable part of network analysis, which has great practical significance. Here, we propose an algorithm IKEoN. Based on the Deep Q-learning algorithm, this algorithm identify the critical edges in the network. Instead of using labeled data sets, IKEoN uses the constant interaction between agents and the environment to train the model, which reduces the influence of network noise and improves the recognition performance. The experimental results show that the proposed method outperforms the existing methods.

AB - The network is a powerful tool to study the interaction of system units, and the edge is an important part of the network as it represents relationships between nodes. Critical edges play an irreplaceable role in information transmission between nodes and maintaining network connectivity and integrity. Therefore, the identification of critical edges in networks is an indispensable part of network analysis, which has great practical significance. Here, we propose an algorithm IKEoN. Based on the Deep Q-learning algorithm, this algorithm identify the critical edges in the network. Instead of using labeled data sets, IKEoN uses the constant interaction between agents and the environment to train the model, which reduces the influence of network noise and improves the recognition performance. The experimental results show that the proposed method outperforms the existing methods.

KW - critical edges

KW - deep reinforcement learning

KW - network

UR - http://www.scopus.com/inward/record.url?scp=85184998015&partnerID=8YFLogxK

U2 - 10.1109/ICICN59530.2023.10393114

DO - 10.1109/ICICN59530.2023.10393114

M3 - 会议稿件

AN - SCOPUS:85184998015

T3 - ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks

SP - 693

EP - 701

BT - ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE 11th International Conference on Information, Communication and Networks, ICICN 2023

Y2 - 17 August 2023 through 20 August 2023

ER -

Wang X, Zeng C, Han L, Zeng X, Wang J, Luo W et al. Finding critical edges in networks through deep reinforcement learning. In ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks. Institute of Electrical and Electronics Engineers Inc. 2023. p. 693-701. (ICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks). doi: 10.1109/ICICN59530.2023.10393114

Finding critical edges in networks through deep reinforcement learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this