Comprehensive analysis of network robustness evaluation based on convolutional neural networks with spatial pyramid pooling

联营 稳健性(进化) 卷积神经网络 计算机科学 人工智能 棱锥(几何) 模式识别(心理学) 机器学习 数学 几何学 生物化学 基因 化学
作者
Wenjun Jiang,Tianlong Fan,Changhao Li,Chuanfu Zhang,Tao Zhang,Zhonghua Luo
出处
期刊:Chaos Solitons & Fractals [Elsevier]
卷期号:184: 115023-115023 被引量:1
标识
DOI:10.1016/j.chaos.2024.115023
摘要

Connectivity robustness, crucial for network understanding, optimization, and repair, has been evaluated traditionally through time-consuming and often impractical simulations. Fortunately, machine learning provides a novel solution. However, unresolved challenges persist: performance in more general edge removal scenarios, capturing robustness via attack curves instead of directly training for robustness, scalability of predictive tasks, and transferability of predictive capabilities. Here, we try to address these challenges by designing a convolutional neural networks (CNN) model with spatial pyramid pooling networks (SPP-net), adapting existing evaluation metrics, redesigning the attack modes, introducing appropriate filtering rules, and incorporating the value of robustness as training data. Results indicate that the CNN framework consistently provides accurate evaluations of attack curves and robustness values across all removal scenarios when the evaluation task aligns with the trained network type. This effectiveness is observed for various network types, failure component types, and failure scenarios, highlighting the scalability in task scale and the transferability in performance of our model. However, the performance of the CNN framework falls short of expectations in various removal scenarios when the predicted task corresponds to a different network type than the one it was trained on, except for random node failures. Furthermore, our work suggests that directly predicting robustness values yields higher accuracy than capturing them through attack curve prediction. In addition, the observed scenario-sensitivity has been overlooked, and the transferability of predictive capability has been overestimated in the evaluation of network features in previous studies, necessitating further optimization. Finally, we discuss several important unresolved questions.
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
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
刚刚
可爱的函函应助tuzhihong采纳,获得10
刚刚
1秒前
阳光幻嫣发布了新的文献求助10
1秒前
3秒前
七七又怪怪完成签到 ,获得积分10
4秒前
9202211125完成签到,获得积分10
6秒前
7秒前
Akim应助柔弱亦寒采纳,获得10
9秒前
9秒前
Paeonia发布了新的文献求助10
9秒前
疯狂大泡芙完成签到,获得积分10
9秒前
wwwww完成签到 ,获得积分10
10秒前
10秒前
NSH完成签到 ,获得积分10
10秒前
情怀应助xx采纳,获得10
12秒前
13秒前
Yu完成签到,获得积分10
13秒前
SciGPT应助好大一只小坏蛋采纳,获得10
14秒前
徐什么宝完成签到,获得积分10
15秒前
Rachel完成签到,获得积分10
15秒前
穆紫应助晓亮采纳,获得10
17秒前
17秒前
完美世界应助海波采纳,获得10
18秒前
18秒前
19秒前
ding应助123采纳,获得10
19秒前
善学以致用应助#include采纳,获得10
20秒前
20秒前
账户已注销应助拾忆采纳,获得30
21秒前
牛顿的苹果完成签到,获得积分10
22秒前
Tonnyjing应助上官蔚蓝采纳,获得10
24秒前
24秒前
柔弱亦寒发布了新的文献求助10
24秒前
hhhhhhh完成签到 ,获得积分10
26秒前
lzx完成签到,获得积分10
26秒前
skyline发布了新的文献求助30
27秒前
catsfat完成签到,获得积分10
28秒前
28秒前
yeahCZY完成签到,获得积分10
28秒前
高分求助中
좌파는 어떻게 좌파가 됐나:한국 급진노동운동의 형성과 궤적 2500
Sustainability in Tides Chemistry 1500
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Cognitive linguistics critical concepts in linguistics 800
Threaded Harmony: A Sustainable Approach to Fashion 799
Livre et militantisme : La Cité éditeur 1958-1967 500
氟盐冷却高温堆非能动余热排出性能及安全分析研究 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3051142
求助须知:如何正确求助?哪些是违规求助? 2708369
关于积分的说明 7412748
捐赠科研通 2352532
什么是DOI,文献DOI怎么找? 1245239
科研通“疑难数据库(出版商)”最低求助积分说明 605536
版权声明 595810