Dynamic Relation-Attentive Graph Neural Networks for Fraud Detection

TL;DR

This paper introduces DRAG, a dynamic relation-attentive graph neural network that adaptively learns relation-specific node representations and combines multi-layer features to improve fraud detection accuracy on heterogeneous graphs.

Contribution

It proposes a novel dynamic relation-attentive aggregation mechanism in GNNs, enhancing fraud detection by considering multiple relation types and multi-layer information.

Findings

DRAG outperforms existing methods on benchmark datasets.

The dynamic attention mechanism improves relation modeling.

Combining multi-layer features enhances detection performance.

Abstract

Fraud detection aims to discover fraudsters deceiving other users by, for example, leaving fake reviews or making abnormal transactions. Graph-based fraud detection methods consider this task as a classification problem with two classes: frauds or normal. We address this problem using Graph Neural Networks (GNNs) by proposing a dynamic relation-attentive aggregation mechanism. Based on the observation that many real-world graphs include different types of relations, we propose to learn a node representation per relation and aggregate the node representations using a learnable attention function that assigns a different attention coefficient to each relation. Furthermore, we combine the node representations from different layers to consider both the local and global structures of a target node, which is beneficial to improving the performance of fraud detection on graphs with heterophily. By employing dynamic graph attention in all the aggregation processes, our method adaptively computes the attention coefficients for each node. Experimental results show that our method, DRAG, outperforms state-of-the-art fraud detection methods on real-world benchmark datasets.