CaT-GNN: Enhancing Credit Card Fraud Detection via Causal Temporal Graph Neural Networks

ArXiv ID: 2402.14708 “View on arXiv”

Authors: Unknown

Abstract

Credit card fraud poses a significant threat to the economy. While Graph Neural Network (GNN)-based fraud detection methods perform well, they often overlook the causal effect of a node’s local structure on predictions. This paper introduces a novel method for credit card fraud detection, the \textbf{"\underline{Ca"}}usal \textbf{"\underline{T"}}emporal \textbf{"\underline{G"}}raph \textbf{"\underline{N"}}eural \textbf{“N”}etwork (CaT-GNN), which leverages causal invariant learning to reveal inherent correlations within transaction data. By decomposing the problem into discovery and intervention phases, CaT-GNN identifies causal nodes within the transaction graph and applies a causal mixup strategy to enhance the model’s robustness and interpretability. CaT-GNN consists of two key components: Causal-Inspector and Causal-Intervener. The Causal-Inspector utilizes attention weights in the temporal attention mechanism to identify causal and environment nodes without introducing additional parameters. Subsequently, the Causal-Intervener performs a causal mixup enhancement on environment nodes based on the set of nodes. Evaluated on three datasets, including a private financial dataset and two public datasets, CaT-GNN demonstrates superior performance over existing state-of-the-art methods. Our findings highlight the potential of integrating causal reasoning with graph neural networks to improve fraud detection capabilities in financial transactions.

Keywords: Graph Neural Networks (GNN), Credit Card Fraud Detection, Causal Invariant Learning, Temporal Graphs, Anomaly Detection

Complexity vs Empirical Score

• Math Complexity: 7.5/10
• Empirical Rigor: 8.0/10
• Quadrant: Holy Grail
• Why: The paper employs advanced causal theory (backdoor adjustment, invariant learning) and complex neural architectures (temporal GNNs, mixup strategies), reflecting high mathematical density. It also demonstrates strong empirical rigor by evaluating on three datasets, including a private financial benchmark, and comparing against state-of-the-art baselines with clear performance metrics.

  flowchart TD
    A["Research Goal<br>Improve Fraud Detection<br>by Incorporating Causal Reasoning"] --> B{"Data Processing"}
    B --> C["Construct Temporal<br>Transaction Graph"]
    C --> D["Phase 1: Causal Discovery<br>Causal-Inspector"]
    D --> E["Identify Causal & Environment Nodes<br>via Temporal Attention Weights"]
    E --> F["Phase 2: Causal Intervention<br>Causal-Intervener"]
    F --> G["Apply Causal Mixup<br>to Environment Nodes"]
    G --> H["Final Model Prediction<br>Enhanced Robustness & Accuracy"]
    H --> I["Outcome: Superior Performance<br>on Financial Datasets<br>vs SOTA Methods"]