Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning

2025-07-08

AI Summary

In graph neural network (GNN)-based fraud detection, severe class imbalance between fraudulent and benign nodes leads to imbalanced topological message propagation and node representation drowning. To address this, we propose MimbFD, a dual-perspective graph representation learning framework. Methodologically, MimbFD jointly models the coupled influence of graph topology and label distribution on supervised message passing—first formalized in this work. It introduces a topology-aware message reachability module to enhance long-range dependency capture for fraudulent nodes, and a local confusion debiasing module to mitigate feature ambiguity induced by adversarial camouflage behaviors of fraudsters. Leveraging a statistics-driven debiasing adjustment strategy during message aggregation, MimbFD achieves significant improvements over state-of-the-art methods across three public fraud detection benchmarks, demonstrating superior accuracy, robustness against adversarial perturbations, and cross-domain generalization capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Graph representation learning has become a mainstream method for fraud detection due to its strong expressive power, which focuses on enhancing node representations through improved neighborhood knowledge capture. However, the focus on local interactions leads to imbalanced transmission of global topological information and increased risk of node-specific information being overwhelmed during aggregation due to the imbalance between fraud and benign nodes. In this paper, we first summarize the impact of topology and class imbalance on downstream tasks in GNN-based fraud detection, as the problem of imbalanced supervisory messages is caused by fraudsters' topological behavior obfuscation and identity feature concealment. Based on statistical validation, we propose a novel dual-view graph representation learning method to mitigate Message imbalance in Fraud Detection(MimbFD). Specifically, we design a topological message reachability module for high-quality node representation learning to penetrate fraudsters' camouflage and alleviate insufficient propagation. Then, we introduce a local confounding debiasing module to adjust node representations, enhancing the stable association between node representations and labels to balance the influence of different classes. Finally, we conducted experiments on three public fraud datasets, and the results demonstrate that MimbFD exhibits outstanding performance in fraud detection.

Problem

• Addressing imbalanced message transmission in fraud detection graphs
• Mitigating fraudsters' camouflage via topological message reachability
• Balancing class influence with local confounding debiasing

Innovation

• Dual-view graph learning balances message imbalance
• Topological message reachability penetrates fraudsters' camouflage
• Local confounding debiasing stabilizes node-label associations