A new approach for evaluating node importance in complex networks via deep learning methods

计算机科学 人工智能 稳健性(进化) 机器学习 图形 排名(信息检索) 深度学习 卷积神经网络 人工神经网络 复杂网络 数据挖掘 理论计算机科学 生物化学 基因 化学 万维网
作者
Min Zhang,Xiaojuan Wang,Lei Jin,Mei Song,Ziyang Li
出处
期刊:Neurocomputing [Elsevier BV]
卷期号:497: 13-27 被引量:37
标识
DOI:10.1016/j.neucom.2022.05.010
摘要

The evaluation of node importance is a critical research topic in network science, widely applied in social networks, transport systems, and computer networks. Prior works addressing this topic either consider a single metric or assign weights for multiple metrics or select features by handcraft, which exist one-sidedness and subjectivity issues. In this paper, to tackle these problems, we propose a new approach named CGNN to identify influential nodes based on deep learning methods, including Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs). CGNN obtains the feature matrices by the contraction algorithm and gets the labels by the Susceptible-Infected-Recovered (SIR) model, which will be leveraged for learning the hidden representations of nodes without utilizing any network metrics as features. We adopt three evaluation criteria to verify CGNN concerning effectiveness and distinguishability, including Kendall’s τ correlation coefficient, monotonicity index (MI), and ranking distribution function (RDF). Nine baselines are employed to compare with CGNN on thirty synthetic networks and twelve real-world networks from different domains. Simulation results demonstrate that CGNN manifests better performance than the baselines, in which the values of τ are large and significantly increase, the values of MI approach to 1, and the points in the RDF curves distribute more uniformly. These results may provide reference significance for controlling epidemic spreading and enhancing network robustness.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
赘婿应助科研通管家采纳,获得10
1秒前
xyy发布了新的文献求助10
2秒前
Dou完成签到,获得积分10
2秒前
闪闪含巧完成签到,获得积分10
3秒前
shouyu29应助华东偏振王采纳,获得10
3秒前
haoduoyu发布了新的文献求助10
4秒前
5秒前
wishait发布了新的文献求助20
6秒前
传奇3应助芋芋采纳,获得10
6秒前
7秒前
Hello应助可靠从云采纳,获得10
8秒前
小紫薯完成签到 ,获得积分10
9秒前
9秒前
蟹子完成签到 ,获得积分10
10秒前
jzyy发布了新的文献求助10
11秒前
hanliulaixi发布了新的文献求助10
12秒前
微醺潮汐完成签到,获得积分10
13秒前
15秒前
游a完成签到,获得积分10
16秒前
芋芋发布了新的文献求助10
18秒前
丘比特应助wishait采纳,获得50
18秒前
19秒前
大模型应助lin采纳,获得10
19秒前
充电宝应助lin采纳,获得50
19秒前
27秒前
nanana发布了新的文献求助10
27秒前
yoyo完成签到,获得积分20
28秒前
30秒前
华仔应助sn采纳,获得10
30秒前
郭一完成签到,获得积分10
30秒前
Akim应助jie采纳,获得10
31秒前
随遇而安应助龙弟弟采纳,获得10
31秒前
33秒前
CodeCraft应助yoyo采纳,获得10
34秒前
34秒前
科研通AI2S应助Ranger_M采纳,获得10
37秒前
斯文败类应助jixuzhuixun采纳,获得10
38秒前
38秒前
淡淡向卉发布了新的文献求助10
39秒前
飘萍过客完成签到,获得积分10
42秒前
高分求助中
Les Mantodea de Guyane Insecta, Polyneoptera 2500
Technologies supporting mass customization of apparel: A pilot project 450
A Field Guide to the Amphibians and Reptiles of Madagascar - Frank Glaw and Miguel Vences - 3rd Edition 400
Brain and Heart The Triumphs and Struggles of a Pediatric Neurosurgeon 400
Cybersecurity Blueprint – Transitioning to Tech 400
Mixing the elements of mass customisation 400
Периодизация спортивной тренировки. Общая теория и её практическое применение 310
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3785875
求助须知:如何正确求助?哪些是违规求助? 3331224
关于积分的说明 10250683
捐赠科研通 3046706
什么是DOI,文献DOI怎么找? 1672190
邀请新用户注册赠送积分活动 801055
科研通“疑难数据库(出版商)”最低求助积分说明 759979