Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-Scale Adaptive Neighborhood Awareness Transformer For Graph Fraud Detection

Jiaqi Lv, Qingfeng Du, Yu Zhang, Yongqi Han, Sheng Li

TL;DR

A multi-scale positional encoding strategy to encode the positional information of various distances from the central node and an embedding fusion strategy is designed for multi-relation graphs, which alleviates the distribution bias caused by different relationships.

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.

Multi-Scale Adaptive Neighborhood Awareness Transformer For Graph Fraud Detection

TL;DR

A multi-scale positional encoding strategy to encode the positional information of various distances from the central node and an embedding fusion strategy is designed for multi-relation graphs, which alleviates the distribution bias caused by different relationships.

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.
Paper Structure (11 sections, 12 equations, 3 figures, 1 table)

This paper contains 11 sections, 12 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Multi-scale Positional Encoding Strategy
  5. Neighborhood Awareness Positional Embedding
  6. Multi-relation Embedding Fusion Strategy
  7. Experiments
  8. Experimental Setup
  9. Fraud Detection Performance
  10. Ablation Study
  11. Conclusion

Figures (3)

  • Figure 1: The overall architecture of MANDATE. For simplicity, we set the number of relationships to 2 as an example.
  • Figure 2: Performance comparison of MANDATE under the diverse positional encoding strategy on the YelpChi and Amazon datasets.
  • Figure 3: Performance comparison of MANDATE under the multi-relation fusion strategy on the YelpChi and Amazon datasets.