Network Dismantling on Signed Network by Evolutionary Deep Reinforcement Learning

Network dismantling is an important question that has attracted much attention from many different research areas, including the disruption of criminal organizations, the maintenance of stability in sensor networks, and so on. However, almost all current algorithms focus on unsigned networks, and fe...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuxuan Ou, Fujing Xiong, Hairong Zhang, Huijia Li
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/24/8026
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102790381764608
author Yuxuan Ou
Fujing Xiong
Hairong Zhang
Huijia Li
author_facet Yuxuan Ou
Fujing Xiong
Hairong Zhang
Huijia Li
author_sort Yuxuan Ou
collection DOAJ
description Network dismantling is an important question that has attracted much attention from many different research areas, including the disruption of criminal organizations, the maintenance of stability in sensor networks, and so on. However, almost all current algorithms focus on unsigned networks, and few studies explore the problem of signed network dismantling due to its complexity and lack of data. Importantly, there is a lack of an effective quality function to assess the performance of signed network dismantling, which seriously restricts its deeper applications. To address these questions, in this paper, we design a new objective function and further propose an effective algorithm named as DSEDR, which aims to search for the best dismantling strategy based on evolutionary deep reinforcement learning. Especially, since the evolutionary computation is able to solve global optimization and the deep reinforcement learning can speed up the network computation, we integrate it for the signed network dismantling efficiently. To verify the performance of DSEDR, we apply it to a series of representative artificial and real network data and compare the efficiency with some popular baseline methods. Based on the experimental results, DSEDR has superior performance to all other methods in both efficiency and interpretability.
format Article
id doaj-art-6cbbb0207fd84574b210330a5ed1884d
institution Kabale University
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-6cbbb0207fd84574b210330a5ed1884d2024-12-27T14:52:45ZengMDPI AGSensors1424-82202024-12-012424802610.3390/s24248026Network Dismantling on Signed Network by Evolutionary Deep Reinforcement LearningYuxuan Ou0Fujing Xiong1Hairong Zhang2Huijia Li3School of Statistics and Data Science, Nankai University, Tianjin 300074, ChinaSchool of Statistics and Data Science, Nankai University, Tianjin 300074, ChinaSchool of Statistics and Data Science, Nankai University, Tianjin 300074, ChinaSchool of Statistics and Data Science, Nankai University, Tianjin 300074, ChinaNetwork dismantling is an important question that has attracted much attention from many different research areas, including the disruption of criminal organizations, the maintenance of stability in sensor networks, and so on. However, almost all current algorithms focus on unsigned networks, and few studies explore the problem of signed network dismantling due to its complexity and lack of data. Importantly, there is a lack of an effective quality function to assess the performance of signed network dismantling, which seriously restricts its deeper applications. To address these questions, in this paper, we design a new objective function and further propose an effective algorithm named as DSEDR, which aims to search for the best dismantling strategy based on evolutionary deep reinforcement learning. Especially, since the evolutionary computation is able to solve global optimization and the deep reinforcement learning can speed up the network computation, we integrate it for the signed network dismantling efficiently. To verify the performance of DSEDR, we apply it to a series of representative artificial and real network data and compare the efficiency with some popular baseline methods. Based on the experimental results, DSEDR has superior performance to all other methods in both efficiency and interpretability.https://www.mdpi.com/1424-8220/24/24/8026signed networknetwork dismantlingevolutionary computationdeep learningreinforcement learning
spellingShingle Yuxuan Ou
Fujing Xiong
Hairong Zhang
Huijia Li
Network Dismantling on Signed Network by Evolutionary Deep Reinforcement Learning
Sensors
signed network
network dismantling
evolutionary computation
deep learning
reinforcement learning
title Network Dismantling on Signed Network by Evolutionary Deep Reinforcement Learning
title_full Network Dismantling on Signed Network by Evolutionary Deep Reinforcement Learning
title_fullStr Network Dismantling on Signed Network by Evolutionary Deep Reinforcement Learning
title_full_unstemmed Network Dismantling on Signed Network by Evolutionary Deep Reinforcement Learning
title_short Network Dismantling on Signed Network by Evolutionary Deep Reinforcement Learning
title_sort network dismantling on signed network by evolutionary deep reinforcement learning
topic signed network
network dismantling
evolutionary computation
deep learning
reinforcement learning
url https://www.mdpi.com/1424-8220/24/24/8026
work_keys_str_mv AT yuxuanou networkdismantlingonsignednetworkbyevolutionarydeepreinforcementlearning
AT fujingxiong networkdismantlingonsignednetworkbyevolutionarydeepreinforcementlearning
AT hairongzhang networkdismantlingonsignednetworkbyevolutionarydeepreinforcementlearning
AT huijiali networkdismantlingonsignednetworkbyevolutionarydeepreinforcementlearning