[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85291-en":3,"doc-seo-85291-105":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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85291,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","A Novel Graph Fraud Detector via Grouped Attribute Completion and Confidence-Aware Contrastive Learning","Graph fraud detection safeguards the security and integrity of modern digital ecosystems such as payments, e-commerce, and social platforms. Existing GNN-based detectors suffer from incomplete node attributes and extreme class imbalance, which degrade representation quality and fraud separability. The paper introduces GFD-GC, a framework combining grouped attribute completion with confidence-aware supervised contrastive learning. Group-wise aggregation imitates heterogeneous neighborhoods, recovering fine-grained node features. Confidence-aware contrastive learning expands scarce labels using high-confidence pseudo-fraud nodes, improving compact fraud representations. Experiments validate state-of-the-art performance on real datasets.","1  \narXiv :2607 . 1 1 107v 1 [ cs .LG] 13 Jul 2026  \nA Novel Graph Fraud Detector via Grouped Attribute Completion and Confidence-Aware  \nContrastive Learning  \n1st Junpeng Wu  \nCollege of Computer and Information Science  \nSouthwest University  \nChongqing, China  \n[junpengw67@gmail.com](junpengw67@gmail.com)  \nYe Yuan*  \nCollege of Computer and Information Science  \nSouthwest University  \nChongqing, China  \n*[yuanyekl@swu.edu.cn](yuanyekl@swu.edu.cn)  \nAbstract  \nGraph fraud detection plays a pivotal role in safeguarding the security and integrity of modern digital ecosystems. Graph Neural Networks (GNNs) are commonly adopted for graph fraud detection. However, the practical performance of existing GNNbased detectors is severely hindered by incomplete node attributes and extreme class imbalance within graphs. To mitigate these limitations, this paper proposes a novel framework for Graph Fraud Detection with Grouped attribute completion and Confidenceaware Contrastive learning, named GFD-GC. Specifically, it first imitates heterogeneous neighborhood structures to implement group-wise aggregation, which obtains informative complete node features by capturing fine-grained graph contextual patterns. Further, it introduces a confidence-aware supervised contrastive learning strategy to augment scarce labeled fraud nodes with highconfidence pseudo-fraud nodes, which enhances the compactness of fraud representations and their separability from non-fraud nodes. Extensive experiments demonstrate the superiority of the proposed GFD-GC over state-of-the-art baselines on the graph fraud detection task, thereby providing an effective solution for real-world fraud scenarios.  \nI. INTRODUCTION  \nThe rapid growth of digital ecosystems, such as online payments, e-commerce platforms, and social networks, has been accompanied by increasing fraudulent activities, causing substantial financial losses and undermining system reliability [1],[2] . In practice, fraud rarely occurs in isolation. Instead, it usually involves complex interactions among users, accounts, devices, merchants, and transactions. Such relations can be naturally modeled as graphs, where fraud detection is formulated as a node classification task on attributed graphs.  \nMotivated by this observation, graph neural networks (GNNs) have been widely used for graph fraud detection, due to their ability to capture structural dependency and neighborhood context [3]–[9],[14],[21],[29],[41],[42],[45],[49],[50],[53],[56],[60],[74]–[81] . Existing graph-based methods have achieved promising results in applications such as electricity theft detection, review spam detection, financial risk control, transaction-network analysis, and social fraud analysis [1], [2], [10]–[14], [52],[54], [59], [61]–[64], [68], [71], [72] . However, their practical performance is still limited in real-world scenarios.  \nThe first challenge is incomplete node attributes. Most GNN-based fraud detectors rely heavily on node features to characterize suspicious behaviors. When features are missing, the learned representations can become unreliable. Although prior studies handle missing attributes through graph-aware incomplete-data modeling or robust representation learning [15]–[17],[25]–[28],[30]–[40],[43],[44],[46]–[48],[51],[55],[57],[58],[64]–[67],[69],[70],[73],[90]–[92], they are mainly designed for general representation learning and do not explicitly model the heterogeneous neighborhood patterns in fraud graphs.  \nThe second challenge is extreme class imbalance. In fraud graphs, fraudulent nodes are much fewer than benign ones, making positive supervision highly insufficient. This often leads to weak fraud representations and unclear decision boundaries. Recent studies show that contrastive learning can improve representation robustness and separability [1], [18], [82]–[89], [93]–[95] . However, directly applying supervised contrastive learning remains inadequate when labeled fraud nodes are extremely scarce.","cbCaitC897lnVRpx","https://ap.wps.com/l/cbCaitC897lnVRpx","pdf",1157903,3,1,9,"English","en",105,"# Introduction\n## Challenges in real-world fraud graphs\n## Proposed framework: GFD-GC\n# Related Work\n## Graph Fraud Detection","[{\"question\":\"What problem does GFD-GC address in graph fraud detection?\",\"answer\":\"GFD-GC addresses incomplete node attributes and extreme class imbalance that limit the practical performance of existing GNN-based fraud detectors.\"},{\"question\":\"How does the grouped attribute completion module work?\",\"answer\":\"It performs group-wise aggregation by imitating heterogeneous neighborhood structures to recover informative, complete node features using fine-grained graph contextual patterns.\"},{\"question\":\"How does confidence-aware supervised contrastive learning improve results?\",\"answer\":\"It augments scarce labeled fraud nodes with high-confidence pseudo-fraud nodes, enhancing the compactness of fraud representations and their separability from non-fraud nodes.\"}]",1784202283,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-novel-graph-fraud-detector-via-grouped-attribute-completion-and-confidence-aware-contrastive-learning","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/a-novel-graph-fraud-detector-via-grouped-attribute-completion-and-confidence-aware-contrastive-learning/85291/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does GFD-GC address in graph fraud detection?","Question",{"text":75,"@type":76},"GFD-GC addresses incomplete node attributes and extreme class imbalance that limit the practical performance of existing GNN-based fraud detectors.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the grouped attribute completion module work?",{"text":80,"@type":76},"It performs group-wise aggregation by imitating heterogeneous neighborhood structures to recover informative, complete node features using fine-grained graph contextual patterns.",{"name":82,"@type":73,"acceptedAnswer":83},"How does confidence-aware supervised contrastive learning improve results?",{"text":84,"@type":76},"It augments scarce labeled fraud nodes with high-confidence pseudo-fraud nodes, enhancing the compactness of fraud representations and their separability from non-fraud nodes.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":21,"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":52,"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":22,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"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"]