[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118779-en":3,"doc-seo-118779-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},118779,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Privacy-Preserving Graph Machine Learning - A Survey - Overview","Graph machine learning often requires data collection, sharing, and analysis across multiple parties, where different stakeholders may demand different privacy guarantees. In big-data settings, complex entity relationships are commonly represented as graphs with both structure and attributes, motivating privacy-preserving variants of modern graph AI. This survey organizes techniques from data generation to privacy-preserving computation, covering secure graph publishing, protection against disclosure and re-identification, and methods for enabling multi-party optimization when sharing is unsafe. The work also reviews supporting theory and tools, outlines open challenges, and envisions an integrated secure graph machine learning system.","Privacy-Preserving Graph Machine Learning from Data to Computation: A Survey  \n􀀃 Dongqi Fu  \ny , Wenxuan Baoy , Ross Maciejewskix , Hanghang Tongy , Jingrui Hey y University of Illinois Urbana-Champaign  \nxArizona State University  \n[dongqif2@illinois.edu](dongqif2@illinois.edu), [wbao4@illinois.edu](wbao4@illinois.edu), [rmacieje@asu.edu](rmacieje@asu.edu), [htong@illinois.edu](htong@illinois.edu), [jingrui@illinois.edu](jingrui@illinois.edu)  \narXiv :2307 .04338v 1 [ cs .LG] 10 Jul 2023  \nABSTRACT  \nIn graph machine learning, data collection, sharing, and analysis often involve multiple parties, each of which may require varying levels of data security and privacy. To this end, preserving privacy is of great importance in protecting sensitive information. In the era of big data, the relationships among data entities have become unprecedentedly complex, and more applications utilize advanced data structures (i.e. , graphs) that can support network structures and relevant attribute information. To date, many graph-based AI models have been proposed (e.g., graph neural networks) for various domain tasks, like computer vision and natural language processing. In this paper, we focus on reviewing privacypreserving techniques of graph machine learning. We systematically review related works from the data to the computational aspects. We 􀀌rst review methods for generating privacy-preserving graph data. Then we describe methods for transmitting privacy-preserved information (e.g., graph model parameters) to realize the optimization-based computation when data sharing among multiple parties is risky or impossible. In addition to discussing relevant theoretical methodology and software tools, we also discuss current challenges and highlight several possible future research opportunities for privacy-preserving graph machine learning. Finally, we envision a uni􀀌ed and comprehensive secure graph machine learning system.  \n1. INTRODUCTION  \nAccording to the recent report from the United Nations 1 , strengthening multilateralism is indispensable to solve the unprecedented challenges in critical areas, such as hunger crisis, misinformation, personal identity disclosure, hate speech, targeted violence, human tra􀀎cking, etc. Addressing these problems requires collaborative e􀀋orts from governments, industry, academia, and individuals. In particular, e􀀋ective and e􀀎cient data collection, sharing, and analysis are atthe core of many decision-making processes, during which preserving privacy is an important topic. Due to the dis  \ntributed, sensitive, and private nature of the large volume of involved data (e.g. , personally identi􀀌able information,􀀃 First two authors contribute equally to this research.  \n1[https://press.un.org/en/2022/sc15140.doc.htm](https://press.un.org/en/2022/sc15140.doc.htm)  \nimages, and video from surveillance cameras or body cameras), it is thus of great importance to make use of the data while avoiding the sharing and use of sensitive information. On the other side, in the era of big data, the relationships among entities have become remarkably complicated. Graph, as a relational data structure, attracts much industrial and research interest for its carrying complex structural and attributed information. For example, with the development of graph neural networks, many application domains have obtained non-trivial improvements, such as computer vision [7], natural language processing [93], recommender systems [85], drug discovery [25], fraud detection [55], etc. Within the trend of applying graph machine learning methods to systematically address problems in various application domains, protecting privacy in the meanwhile is nonneglectable [20] . To this end, we consider two complementary strategies in this survey, namely, (1) to share faithfully generated graph data instead of the actual sensitive graph data, and (2) to enable multi-party computation without graph data sharing. Inspired by the above discussion, we focus","cbCaisLgeMGLCtj1","https://ap.wps.com/l/cbCaisLgeMGLCtj1","pdf",3091973,1,20,"English","en",105,"# Introduction\n## Privacy-Preserving Graph Data\n## Attackers and Background Knowledge\n## Protection Mechanisms\n## Statistical Properties and Challenges\n# Graph Data Privacy-Preserving Computation\n## Federated/Multi-party Computation Framework","[{\"question\":\"What two complementary strategies does the survey emphasize for privacy-preserving graph machine learning?\",\"answer\":\"The survey highlights sharing faithfully generated privacy-preserving graph data instead of the original sensitive graph, and enabling multi-party computation without sharing graph data.\"},{\"question\":\"How does the survey structure the privacy-preserving graph data topic?\",\"answer\":\"It reviews attackers and their required background knowledge, explains protection mechanisms against disclosure and link re-identification, and further covers privacy methods for graph statistical properties and challenges such as time-evolving and heterogeneous graphs.\"},{\"question\":\"What is the focus of the computation aspect in this survey?\",\"answer\":\"It focuses on multi-party computation scenarios where optimization-based computation is carried out while avoiding direct graph data transmission, such as in federated learning using model parameters instead.\"}]","Privacy-Preserving Graph Machine Learning - A Survey - Overview | PDF",1785720207,50,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"privacy-preserving-graph-machine-learning-a-survey-overview","",{"@graph":36,"@context":86},[37,54,69],{"@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-graph-machine-learning-a-survey-overview/118779/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What two complementary strategies does the survey emphasize for privacy-preserving graph machine learning?","Question",{"text":76,"@type":77},"The survey highlights sharing faithfully generated privacy-preserving graph data instead of the original sensitive graph, and enabling multi-party computation without sharing graph data.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the survey structure the privacy-preserving graph data topic?",{"text":81,"@type":77},"It reviews attackers and their required background knowledge, explains protection mechanisms against disclosure and link re-identification, and further covers privacy methods for graph statistical properties and challenges such as time-evolving and heterogeneous graphs.",{"name":83,"@type":74,"acceptedAnswer":84},"What is the focus of the computation aspect in this survey?",{"text":85,"@type":77},"It focuses on multi-party computation scenarios where optimization-based computation is carried out while avoiding direct graph data transmission, such as in federated learning using model parameters instead.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":29,"slug":114},6,"Technology","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":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":21,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":21,"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":107,"slug":137},19,"General","general"]