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

Paper: arXiv 2402.14708

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.

Complexity vs Empirical Score

• Math Complexity: 7.5/10
• Empirical Rigor: 8.0/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: 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.

Research Flowchart

  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"]

Cited References (106)

1. Suspicious behavior detection: Current trends and future directions (2016)
2. From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews (2013)
3. Open graph benchmark: Datasets for machine learning on graphs (2020)
4. Should graph convolution trust neighbors? a simple causal inference method (2021)
5. Collective opinion spam detection: Bridging review networks and metadata (2015)
6. Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective (2023) — link
7. Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment (2023)
8. Attend who is weak: Enhancing graph condensation via cross-free adversarial training (2023) — link

1 of 106 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.