[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121182-en":3,"doc-seo-121182-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121182,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Privacy-Preserving Vital Node Identification in Complex Networks using Machine Learning","Identifying vital nodes in complex networks is essential across social network analysis, epidemiology, and physics, yet it is constrained by privacy restrictions when network data are sensitive (e.g., Bluetooth-based contact networks). This study presents a machine learning approach that learns from the outputs of vital node identification algorithms. Results show strong performance even when trained on only 20% of the data, outperforming state-of-the-art methods under severe information limits and advancing privacy-centric network analysis.","Privacy-Preserving Vital Node Identification in Complex Networks using Machine Learning  \nDiaoul´e Diallo and Tobias Hecking  \nGerman Aerospace Center, 51147 Linder H¨ohe, Germany [diaoule.diallo@dlr.de](diaoule.diallo@dlr.de)  \nAbstract. Identifying vital nodes in complex networks is critical in various research areas, including social network analysis, epidemiology, and physics. Centrality measures are commonly used and combined for this purpose. However, vital node identification is often hindered due to privacy restrictions, particularly in networks built from sensitive data like Bluetooth-based contact networks. This study introduces a machine learning-based approach that leverages the outputs of vital node identification algorithms. Our approach demonstrates that, even when trained on just 20 percent of the data, our proposed models can significantly outperform state-of-the-art methods, particularly in scenarios where network information is severely limited. This research advances the understanding of privacy-centric methods in complex network analysis and shows how machine learning can enhance vital node identification under privacy-preserving conditions.  \nKeywords: vital node identification, influential node ranking, machine learning, privacy-sensitive network analysis, epidemic modeling and analysis  \n1 Introduction  \nIdentifying crucial nodes within complex networks has long been a central focus in network science, with applications across various domains, including information dissemination [34], power grid analysis [2], economics [12], and infectious disease modeling [4] . In these areas, a vital node is typically defined as one that significantly influences both the functionality and structure of the network [24] .  \nThe relevance of vital node identification has become particularly evident in the context of infectious disease modeling, as underscored by the COVID-19 pandemic [8,11] . Identifying these nodes is crucial not only for predicting and controlling the spread of infections during pandemics but also for helping individuals to understand their potential role in transmission processes and their risk of infection. Recent advancements, such as Bluetooth-based contact tracing apps, have been promoted as tools for assessing individual infection risk and detecting outbreaks [32] . However, these apps initially struggled with user acceptance due to privacy concerns. This led to the adoption of decentralized approaches, where anonymized contact data is stored directly on user devices. As a result,  \n2 Diaoul´e Diallo et al.  \nonly limited, localized network information is available, restricting the accuracy of infection risk estimation. This limitation underscores a critical trade-off between the precision of vital node estimation and the constraints imposed by data protection regulations.  \nIn our previous work [10], we explored the efficacy of centrality measures for identifying vital nodes in complex networks under privacy constraints, examining algorithm properties and the role of network characteristics. Our experimental results indicate that the spreading capability (or vitality) of a node can in many cases accurately be estimated by only considering its up-to seconddegree neighbors. In this work, we build upon these findings and introduce a machine learning-based approach that utilizes outputs of the most promising vital node identification algorithms (VN algorithms) . Our approach shows better performance compared to existing methods, especially in scenarios with severely limited network information. This not only deepens the understanding of privacy-centric methods in complex network analysis but also demonstrates the potential of machine learning-based techniques to enhance network analysis under privacy-preserving conditions.  \nWe initially offer a background on node vitality and privacy in Section 2 . This is followed by a detailed explanation of the experimental setup and an overview of vital node id","cbCaihntvEiFt688","https://ap.wps.com/l/cbCaihntvEiFt688","pdf",396624,1,12,"English","en",105,"# Introduction\n## Motivation and applications\n## Privacy constraints in contact networks\n## Prior work and contribution\n# Background\n## Node vitality vs. influence maximization\n## Centrality-based vitality measures\n## Categories of vital node identification algorithms\n# Experimental setup and algorithms\n## Experimental setup\n## Vital node identification algorithms (VN algorithms)\n# Proposed machine learning method\n## Method overview\n# Results and discussion\n## Findings and implications for privacy-aware identification\n# Conclusion","[{\"question\":\"What is the main problem addressed in this study?\",\"answer\":\"The study targets the difficulty of identifying vital nodes when privacy restrictions severely limit available network information, especially for sensitive Bluetooth-based contact networks.\"},{\"question\":\"How does the proposed method improve vital node identification under limited data?\",\"answer\":\"It uses a machine learning model trained on outputs from existing vital node identification algorithms, achieving strong performance even with training on only 20% of the data.\"},{\"question\":\"What are the key categories of vital node identification algorithms described in the background?\",\"answer\":\"The background groups methods into local, semi-local, global, and hybrid algorithms, differing in how much of a node’s neighborhood or the entire network structure they use.\"}]","Privacy-Preserving Vital Node Identification in Complex Networks using Machine Learning | PDF",1785734244,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"privacy-preserving-vital-node-identification-in-complex-networks-using-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/privacy-preserving-vital-node-identification-in-complex-networks-using-machine-learning/121182/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main problem addressed in this study?","Question",{"text":75,"@type":76},"The study targets the difficulty of identifying vital nodes when privacy restrictions severely limit available network information, especially for sensitive Bluetooth-based contact networks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method improve vital node identification under limited data?",{"text":80,"@type":76},"It uses a machine learning model trained on outputs from existing vital node identification algorithms, achieving strong performance even with training on only 20% of the data.",{"name":82,"@type":73,"acceptedAnswer":83},"What are the key categories of vital node identification algorithms described in the background?",{"text":84,"@type":76},"The background groups methods into local, semi-local, global, and hybrid algorithms, differing in how much of a node’s neighborhood or the entire network structure they use.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]