Litcius/Paper detail

Explainable Graph-based Fraud Detection via Neural Meta-graph Search

Zidi Qin, Yang Liu, Qing He, Xiang Ao

2022Proceedings of the 31st ACM International Conference on Information & Knowledge Management29 citationsDOIOpen Access PDF

Abstract

Though graph neural networks (GNNs)-based fraud detectors have received remarkable success in identifying fraudulent activities, few of them pay equal attention to models' performance and explainability. In this paper, we attempt to achieve high performance for graph-based fraud detection while considering model explainability. We propose NGS (Neural meta-Graph Search), in which the message passing process of a GNN is formalized as a meta-graph, and a differentiable neural architecture search is devised to determine the optimized message passing graph structure. We further enhance the model by aggregating multiple searched meta-graphs to make the final prediction. Experimental results on two real-world datasets demonstrate that NGS outperforms state-of-the-art baselines. In addition, the searched meta-graphs concisely describe the information used for prediction and produce reasonable explanations.

Topics & Concepts

Computer scienceGraphDifferentiable functionArtificial neural networkTheoretical computer scienceMessage passingData miningMachine learningArtificial intelligenceDistributed computingMathematicsMathematical analysisAdvanced Graph Neural NetworksImbalanced Data Classification TechniquesExplainable Artificial Intelligence (XAI)
Explainable Graph-based Fraud Detection via Neural Meta-graph Search | Litcius