Multi-Scale Adaptive Neighborhood Awareness Transformer For Graph Fraud Detection

TL;DR

This paper introduces MANDATE, a multi-scale transformer model that improves graph fraud detection by addressing GNN limitations through enhanced global modeling and relation-aware embeddings.

Contribution

The paper proposes a novel multi-scale positional encoding and embedding strategies to mitigate GNN biases and enhance global context understanding in fraud detection.

Findings

MANDATE outperforms existing methods on three datasets.

Enhanced global modeling improves detection accuracy.

Relation-aware embeddings reduce distribution bias.

Abstract

Graph fraud detection (GFD) is crucial for identifying fraudulent behavior within graphs, benefiting various domains such as financial networks and social media. Existing methods based on graph neural networks (GNNs) have succeeded considerably due to their effective expressive capacity for graph-structured data. However, the inherent inductive bias of GNNs, including the homogeneity assumption and the limited global modeling ability, hinder the effectiveness of these models. To address these challenges, we propose Multi-scale Neighborhood Awareness Transformer (MANDATE), which alleviates the inherent inductive bias of GNNs. Specifically, we design a multi-scale positional encoding strategy to encode the positional information of various distances from the central node. By incorporating it with the self-attention mechanism, the global modeling ability can be enhanced significantly. Meanwhile, we design different embedding strategies for homophilic and heterophilic connections. This mitigates the homophily distribution differences between benign and fraudulent nodes. Moreover, an embedding fusion strategy is designed for multi-relation graphs, which alleviates the distribution bias caused by different relationships. Experiments on three fraud detection datasets demonstrate the superiority of MANDATE.