[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118111-en":3,"doc-seo-118111-105":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},118111,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Towards Data Privacy and Utility in the Applications of Graph Neural Networks","Graph Neural Networks (GNNs) support learning from graph-structured data, yet such graphs often include sensitive information. Maintaining privacy without losing usability motivates this dissertation, which presents three studies targeting node classification, link prediction, and graph classification. The work develops adversarial learning for link-privacy-preserved graph embeddings for social networks, validated on real data. It then proposes PPFL-GNN to improve federated GNN learning under non-IID client data by reducing client overfitting and server aggregation inefficiency via embedding alignment. Finally, it introduces a meta-learning plus contrastive framework for few-shot graph classification on molecular and social datasets, along with benchmark datasets. ","ScholarWorks@GSU  \nTowards Data Privacy and Utility in the Applications of Graph Neural Networks  \n\n| Authors | Zhang, Kainan |\n| --- | --- |\n| Citation | Zhang , Kainan (2023) . Towards Data Privacy and Utility in the Applications of Graph Neural Networks. Dissertation , Georgia State University. [https://doi.org/10.57709/36369498](https://doi.org/10.57709/36369498) |\n| DOI | [https://doi.org/10.57709/36369498](https://doi.org/10.57709/36369498) |\n| Download date | 2026-03-07 01:17:18 |\n| Link to Item | [https://hdl.handle. net/20.500.14694/3985](https://hdl.handle. net/20.500.14694/3985) |\n\nTowards Data Privacy and Utility in the Applications of Graph Neural Networks  \nby  \nKainan Zhang  \nUnder the Direction of Zhipeng Cai, Ph.D.  \nA Dissertation Submitted in Partial Fulfillment of the Requirements for the Degree of  \nDoctor of Philosophy  \nin the College of Arts and Sciences  \nGeorgia State University  \nABSTRACT  \nGraph Neural Networks (GNNs) are essential for handling graph-structured data, often containing sensitive information. It’s vital to maintain a balance between data privacy and usability. To address this, this dissertation introduces three studies aimed at enhancing privacy and utility in GNN applications, particularly in node classification, link prediction, and graph classification. The first work tackles celebrity privacy in social networks. We develop a novel framework using adversarial learning for link-privacy preserved graph embedding, which effectively safeguards sensitive links without compromising the graph’s structure and node attributes. This approach is validated using real social network data. In the second work, we confront challenges in federated graph learning with non-independent and identically distributed (non-IID) data. We introduce PPFL-GNN, a privacy-preserving federated graph neural network framework that mitigates overfitting on the client side and inefficient aggregation on the server side. It leverages local graph data for embeddings and employs embedding alignment techniques for enhanced privacy, addressing the hurdles in federated learning on non-IID graph data. The third work explores Few-Shot graph classification, which aims to classify novel graph types with limited labeled data. We propose a unique framework combining Meta-learning and contrastive learning to better utilize graph structures in molecular and social network datasets. Additionally, we offer benchmark graph datasets with extensive node-attribute dimensions for future research. These studies collectively advance the field of graph-based machine learning by addressing critical issues of data privacy and utility in GNN applications.  \nINDEX WORDS: Machine Learning, Graph Neural Networks, Privacy Preserva  \ntion  \nCopyright by Kainan Zhang 2023  \nTowards Data Privacy and Utility in the Applications of Graph Neural Networks  \nby  \nKainan Zhang  \nCommittee Chair:  \nCommittee:  \nZhipeng Cai  \nZhipeng Cai Yingshu Li Wei Li  \nYan Huang  \nElectronic Version Approved:  \nOffice of Graduate Studies College of Arts and Sciences Georgia State University  \nDecember 2023  \nv  \nDEDICATION  \nI dedicate this dissertation to my family, especially my parents, Zhengyu Zhang and Zhongying Li. Their unwavering encouragement and heartfelt words have been my guiding light throughout this journey.  \nI also extend my gratitude to my friends and colleagues. Their steadfast support and companionship during this doctoral program have been invaluable. Their contributions, in myriad ways, have enriched this endeavor, and I’m eternally thankful.  \nEmbarking on this Ph.D. journey introduced me to the complexities and nuances of computer science. Beyond algorithms and codes, I learned about resilience, perseverance, and the insatiable thirst for knowledge. As I pause to reflect on this significant chapter, I’m reminded that in the vast canvas of computer science, every byte of data has an untold story, and every line of code is a legacy in the making.  \nv","cbCaigqU7hSLzPTn","https://ap.wps.com/l/cbCaigqU7hSLzPTn","pdf",2651632,1,112,"English","en",105,"# Acknowledgments\n# List of Tables\n# List of Figures\n# 1 Introduction\n## 1.1 Background of Graph Learning\n## 1.2 Privacy Issues in Graph Neural Networks\n## 1.3 Federated Graph Learning on Non-IID Graph Data\n## 1.4 Few-Shot Graph Learning\n# 2 Related Works\n## 2.1 Graph Neural Networks\n## 2.2 Link Privacy Preservation in Social Networks\n## 2.3 Federated Learning","[{\"question\":\"What problem does the dissertation address in Graph Neural Networks?\",\"answer\":\"It addresses the need to balance data privacy with usability when applying GNNs to sensitive graph-structured information.\"},{\"question\":\"How does the first study preserve link privacy while keeping graph utility?\",\"answer\":\"It uses adversarial learning to produce link-privacy-preserved graph embeddings that safeguard sensitive links while preserving graph structure and node attributes.\"},{\"question\":\"What is PPFL-GNN designed to handle in federated graph learning?\",\"answer\":\"PPFL-GNN mitigates client-side overfitting and server-side inefficient aggregation under non-IID graph data using local embeddings and embedding alignment for enhanced privacy.\"}]","Towards Data Privacy and Utility in the Applications of Graph Neural Networks | PDF",1785681663,282,{"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},"towards-data-privacy-and-utility-in-the-applications-of-graph-neural-networks","",{"@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/towards-data-privacy-and-utility-in-the-applications-of-graph-neural-networks/118111/",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","2026-08-02",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 problem does the dissertation address in Graph Neural Networks?","Question",{"text":75,"@type":76},"It addresses the need to balance data privacy with usability when applying GNNs to sensitive graph-structured information.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the first study preserve link privacy while keeping graph utility?",{"text":80,"@type":76},"It uses adversarial learning to produce link-privacy-preserved graph embeddings that safeguard sensitive links while preserving graph structure and node attributes.",{"name":82,"@type":73,"acceptedAnswer":83},"What is PPFL-GNN designed to handle in federated graph learning?",{"text":84,"@type":76},"PPFL-GNN mitigates client-side overfitting and server-side inefficient aggregation under non-IID graph data using local embeddings and embedding alignment for enhanced privacy.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]