6 January 2023 in IEEE Transactions on Big Data
Graphs have been widely adopted to accomplish fraud detection tasks because of their inherently favorable structure to capture the intricate features in many complicated scenarios, especially in some modern e-commerce situations that have various relation attributes like transactions. These works tend to utilize the direct aggregate information about neighbor nodes of the target node or the aggregation of the neighbor information after the conditional filter and mostly use local information but ignore global information. However, in some cases, local abnormal points are detected in the global view, so global information is very important for fraud detection. In this article, we propose a local and global aware memory-based graph neural network for fraud detection (LGM-GNN). It first obtains the preliminary node embedding through relation-aware embedding and then interactively aggregates the local and global memory network to fuse and utilize the local and global information. Finally, the node embeddings of different levels are aggregated through the hierarchical information aggregator. Extensive experiments show our proposed LGM-GNN outperforms other SOAT methods on two real-world fraud detection datasets.
27 June 2024 in IEEE Transactions on Artificial Intelligence
With the development of the e-commerce platform, more and more reviews of its various formats continue to appear. Reviews help people buy the right item faster, and instead, spam reviews reduce the user experience. To be able to detect spam reviews, statistical machine learning-based methods were commonly used in the past, but these approaches ignored the correlation between reviews. With the development of the graph fraud detection model, people have started to graph model the review data. However, typical graph fraud detection models still have problems with interpretability. Therefore, we propose here an IN terpretable G raph F raud D etection model for spam reviews, which is also named IN-GFD. As for the interpretability issue, we leveraged the relationship against the predicted score and whether a review is spam or not to build a loss function on top of the feature-embedding matrix, and introduced a scoring difference threshold mechanism, which can allow our model to have ante-hoc interpretability. In addition, to address class imbalance issues, IN-GFD utilizes the oversampling of the spam nodes to balance them with normal nodes and introduces an edge-loss function to learn new edge relationships. After extensive experiments, our method proves to be better than other State Of The Arts (SOTA) models in terms of fraud detection and offers the benefit of interpretability. Finally, our study combines detection models with ante-hoc interpretability, offering a promising direction in review detection. Our approach has wide applicability, detecting spam reviews in datasets with user reviews and providing reasonable interpretations.
13 December 2024 in IEEE Transactions on Big Data
The mass volume of data in the modern business world requires fraud detection to be automated. Hence, some researchers constructed the fraud scenario into graph data and proposed graph-based fraud detection methods. These methods treat the problem of fraud detection as a binary node classification task. However, the differences between the nodes of the same class are ignored. In this paper, we try to distinguish differences in behavior among nodes of the same class to improve the model's ability to detect deviation, i.e., we make a fine-grained classification of user behavior (called prototypes) and propose an adaptive prototype-based graph neural network (APGNN) for fraud detection. APGNN learns node behavior representations by extracting both neighborhood and global information, supplying preliminary knowledge for the adaptive creation of several prototypes, each representing a distinct behavior pattern. Subsequently, a new loss function is employed to enhance the prototypes' capacity to capture these behavior patterns and to amplify the feature differences between different prototypes. Nodes are then projected onto these prototypes to derive the final behavior patterns. Extensive experiments on four real-world datasets show that this method can provide better fraud detection as well as a more understandable result.
10 April 2026 in ACM Transactions on Knowledge Discovery From Data
Unsupervised graph anomaly detection seeks to discover rare patterns in graph-structured data, enabling applications across diverse fields such as financial transactions, e-commerce, and beyond. Although recent methods based on graph autoencoder and graph contrastive consistency show considerable promise in this field, the former primarily addresses global anomalies, whereas the latter is more focused on local anomalies. This distinction limits their capacity to fully capture the abnormalities of nodes in the graph. Moreover, challenges such as overfitting of abnormal patterns and the introduction of unknown noise from random walk-based subgraph sampling remain prevalent. These issues contribute to suboptimal model performance. To tackle these challenges, we propose Local and Global Contrastive Networks (LGCN). LGCN first extracts graph features using a feature encoder module and subsequently projects them into local and global feature subspaces. The global information learning module mitigates overfitting in reconstruction techniques to abnormal patterns by simultaneously accounting for both the similarities and differences between nodes. The local information learning module extracts anomaly information by evaluating the consistency between the center node and its corresponding context features. Extensive experiments across eight datasets demonstrate that LGCN outperforms existing methods in unsupervised graph anomaly detection.