Clustering-Augmented Fraud Detection on Graphs Using Label-Aware Feature Aggregation

Shixiong Jing, Lingwei Chen, Dinghao Wu
Proceedings of the 16th Asian Conference on Machine Learning, PMLR 260:1272-1287, 2025.

Abstract

Fraud detection has emerged as a pivotal process in different fields (e.g., e-commerce, social networks). Since interactions among entities provide valuable insights into fraudulent activities, such behaviors can be naturally represented as graphs, where graph neural networks (GNNs) have been developed as prominent models to boost the efficacy of fraud detection. However, the application of GNNs in this domain encounters significant challenges, primarily due to class imbalance and a mixture of homophily and heterophily of fraud graphs. To address these challenges, in this paper, we propose LACA, which implements fraud detection on graphs using Label-Aware feature aggregation to advance GNN training, which is regularized by Clustering Augmented optimization. Specifically, label-aware feature aggregation simplifies adaptive aggregation in homophily-heterophily mixed neighborhoods, preventing gradient domination by legitimate nodes and mitigating class imbalance in message passing. Clustering-augmented optimization provides fine-grained subclass semantics to improve detection performance, and yields additional benefit in addressing class imbalance. Extensive experiments on four fraud datasets demonstrate that LACA can significantly improve fraud detection performance on graphs with different imbalance ratios and homophily ratios, outperforming state-of-the-art GNN models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v260-jing25a, title = {Clustering-Augmented Fraud Detection on Graphs Using Label-Aware Feature Aggregation}, author = {Jing, Shixiong and Chen, Lingwei and Wu, Dinghao}, booktitle = {Proceedings of the 16th Asian Conference on Machine Learning}, pages = {1272--1287}, year = {2025}, editor = {Nguyen, Vu and Lin, Hsuan-Tien}, volume = {260}, series = {Proceedings of Machine Learning Research}, month = {05--08 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v260/main/assets/jing25a/jing25a.pdf}, url = {https://proceedings.mlr.press/v260/jing25a.html}, abstract = {Fraud detection has emerged as a pivotal process in different fields (e.g., e-commerce, social networks). Since interactions among entities provide valuable insights into fraudulent activities, such behaviors can be naturally represented as graphs, where graph neural networks (GNNs) have been developed as prominent models to boost the efficacy of fraud detection. However, the application of GNNs in this domain encounters significant challenges, primarily due to class imbalance and a mixture of homophily and heterophily of fraud graphs. To address these challenges, in this paper, we propose LACA, which implements fraud detection on graphs using Label-Aware feature aggregation to advance GNN training, which is regularized by Clustering Augmented optimization. Specifically, label-aware feature aggregation simplifies adaptive aggregation in homophily-heterophily mixed neighborhoods, preventing gradient domination by legitimate nodes and mitigating class imbalance in message passing. Clustering-augmented optimization provides fine-grained subclass semantics to improve detection performance, and yields additional benefit in addressing class imbalance. Extensive experiments on four fraud datasets demonstrate that LACA can significantly improve fraud detection performance on graphs with different imbalance ratios and homophily ratios, outperforming state-of-the-art GNN models.} }
Endnote
%0 Conference Paper %T Clustering-Augmented Fraud Detection on Graphs Using Label-Aware Feature Aggregation %A Shixiong Jing %A Lingwei Chen %A Dinghao Wu %B Proceedings of the 16th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Vu Nguyen %E Hsuan-Tien Lin %F pmlr-v260-jing25a %I PMLR %P 1272--1287 %U https://proceedings.mlr.press/v260/jing25a.html %V 260 %X Fraud detection has emerged as a pivotal process in different fields (e.g., e-commerce, social networks). Since interactions among entities provide valuable insights into fraudulent activities, such behaviors can be naturally represented as graphs, where graph neural networks (GNNs) have been developed as prominent models to boost the efficacy of fraud detection. However, the application of GNNs in this domain encounters significant challenges, primarily due to class imbalance and a mixture of homophily and heterophily of fraud graphs. To address these challenges, in this paper, we propose LACA, which implements fraud detection on graphs using Label-Aware feature aggregation to advance GNN training, which is regularized by Clustering Augmented optimization. Specifically, label-aware feature aggregation simplifies adaptive aggregation in homophily-heterophily mixed neighborhoods, preventing gradient domination by legitimate nodes and mitigating class imbalance in message passing. Clustering-augmented optimization provides fine-grained subclass semantics to improve detection performance, and yields additional benefit in addressing class imbalance. Extensive experiments on four fraud datasets demonstrate that LACA can significantly improve fraud detection performance on graphs with different imbalance ratios and homophily ratios, outperforming state-of-the-art GNN models.
APA
Jing, S., Chen, L. & Wu, D.. (2025). Clustering-Augmented Fraud Detection on Graphs Using Label-Aware Feature Aggregation. Proceedings of the 16th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 260:1272-1287 Available from https://proceedings.mlr.press/v260/jing25a.html.

Related Material