GNN-EADD: Graph Neural Network-Based E-Commerce Anomaly Detection via Dual-Stage Learning
E-commerce platforms face significant challenges in detecting anomalous products, including counterfeit goods and fraudulent listings, which can undermine user trust and platform integrity. This paper presents Graph Neural Network-based E-commerce Anomaly Detection via Dual-stage Learning (GNN-EADD)...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10829566/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592931712663552 |
|---|---|
| author | Zhouhang Shao Xuran Wang Enkai Ji Shiyang Chen Jin Wang |
| author_facet | Zhouhang Shao Xuran Wang Enkai Ji Shiyang Chen Jin Wang |
| author_sort | Zhouhang Shao |
| collection | DOAJ |
| description | E-commerce platforms face significant challenges in detecting anomalous products, including counterfeit goods and fraudulent listings, which can undermine user trust and platform integrity. This paper presents Graph Neural Network-based E-commerce Anomaly Detection via Dual-stage Learning (GNN-EADD), a novel approach leveraging graph neural networks for anomaly detection in large-scale e-commerce ecosystems. Our key contributions include: 1) A heterogeneous graph representation incorporating products, sellers, and buyers as nodes with their relationships as edges; 2) A novel dual-stage learning framework combining unsupervised graph embedding with semi-supervised fine-tuning; and 3) An attention mechanism that effectively captures complex patterns within network structures. Extensive experiments on a large-scale Amazon dataset demonstrate that GNN-EADD significantly outperforms state-of-the-art baselines in terms of anomaly detection accuracy, precision, and recall, while showing robustness to various types of anomalies and scalability to large networks. |
| format | Article |
| id | doaj-art-6e308860ae2a445b9b24584d018ecf83 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6e308860ae2a445b9b24584d018ecf832025-01-21T00:01:34ZengIEEEIEEE Access2169-35362025-01-01138963897610.1109/ACCESS.2025.352623910829566GNN-EADD: Graph Neural Network-Based E-Commerce Anomaly Detection via Dual-Stage LearningZhouhang Shao0https://orcid.org/0009-0004-5262-3960Xuran Wang1https://orcid.org/0009-0001-1626-5527Enkai Ji2Shiyang Chen3https://orcid.org/0009-0003-7099-3511Jin Wang4Department of Computer Science and Engineering, University of California San Diego, La Jolla, CA, USADepartment of Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USADepartment of Computer Science, Rutgers University, New Brunswick, NJ, USACollege of Engineering, Texas A&M University, College Station, TX, USAViterbi School of Engineering, University of Southern California, Los Angeles, CA, USAE-commerce platforms face significant challenges in detecting anomalous products, including counterfeit goods and fraudulent listings, which can undermine user trust and platform integrity. This paper presents Graph Neural Network-based E-commerce Anomaly Detection via Dual-stage Learning (GNN-EADD), a novel approach leveraging graph neural networks for anomaly detection in large-scale e-commerce ecosystems. Our key contributions include: 1) A heterogeneous graph representation incorporating products, sellers, and buyers as nodes with their relationships as edges; 2) A novel dual-stage learning framework combining unsupervised graph embedding with semi-supervised fine-tuning; and 3) An attention mechanism that effectively captures complex patterns within network structures. Extensive experiments on a large-scale Amazon dataset demonstrate that GNN-EADD significantly outperforms state-of-the-art baselines in terms of anomaly detection accuracy, precision, and recall, while showing robustness to various types of anomalies and scalability to large networks.https://ieeexplore.ieee.org/document/10829566/Graph neural networkse-commerceanomaly detectionheterogeneous graphsgraph attention networks |
| spellingShingle | Zhouhang Shao Xuran Wang Enkai Ji Shiyang Chen Jin Wang GNN-EADD: Graph Neural Network-Based E-Commerce Anomaly Detection via Dual-Stage Learning IEEE Access Graph neural networks e-commerce anomaly detection heterogeneous graphs graph attention networks |
| title | GNN-EADD: Graph Neural Network-Based E-Commerce Anomaly Detection via Dual-Stage Learning |
| title_full | GNN-EADD: Graph Neural Network-Based E-Commerce Anomaly Detection via Dual-Stage Learning |
| title_fullStr | GNN-EADD: Graph Neural Network-Based E-Commerce Anomaly Detection via Dual-Stage Learning |
| title_full_unstemmed | GNN-EADD: Graph Neural Network-Based E-Commerce Anomaly Detection via Dual-Stage Learning |
| title_short | GNN-EADD: Graph Neural Network-Based E-Commerce Anomaly Detection via Dual-Stage Learning |
| title_sort | gnn eadd graph neural network based e commerce anomaly detection via dual stage learning |
| topic | Graph neural networks e-commerce anomaly detection heterogeneous graphs graph attention networks |
| url | https://ieeexplore.ieee.org/document/10829566/ |
| work_keys_str_mv | AT zhouhangshao gnneaddgraphneuralnetworkbasedecommerceanomalydetectionviadualstagelearning AT xuranwang gnneaddgraphneuralnetworkbasedecommerceanomalydetectionviadualstagelearning AT enkaiji gnneaddgraphneuralnetworkbasedecommerceanomalydetectionviadualstagelearning AT shiyangchen gnneaddgraphneuralnetworkbasedecommerceanomalydetectionviadualstagelearning AT jinwang gnneaddgraphneuralnetworkbasedecommerceanomalydetectionviadualstagelearning |