Graph Neural Network with One-side Edge Sampling for Fraud Detection

TL;DR

This paper introduces One-Side Edge Sampling (OES), a method for improving Graph Neural Network training efficiency and robustness against over-smoothing and over-fitting in fraud detection tasks.

Contribution

The paper proposes OES, a novel sampling technique based on predictive confidence, with theoretical analysis and empirical validation demonstrating its effectiveness.

Findings

OES reduces training time for GNNs.

OES improves performance of shallow and deep GNNs.

OES alleviates over-smoothing and over-fitting issues.

Abstract

Financial fraud is always a major problem in the field of finance, as it can cause significant consequences. As a result, many approaches have been designed to detect it, and lately Graph Neural Networks (GNNs) have been demonstrated as a competent candidate. However, when trained with a large amount of data, they are slow and computationally demanding. In addition, GNNs may need a deep architecture to detect complex fraud patterns, but doing so may make them suffer from problems such as over-fitting or over-smoothing. Over-fitting leads to reduced generalisation of the model on unseen data, while over-smoothing causes all nodes' features to converge to a fixed point due to excessive aggregation of information from neighbouring nodes. In this research, I propose an approach called One-Side Edge Sampling (OES) that can potentially reduce training duration as well as the effects of over-smoothing and over-fitting. The approach leverages predictive confidence in an edge classification task to sample edges from the input graph during a certain number of epochs. To explain why OES can alleviate over-smoothing, I perform a theoretical analysis of the proposed approach. In addition, to validate the effect of OES, I conduct experiments using different GNNs on two datasets. The results show that OES can empirically outperform backbone models in both shallow and deep architectures while also reducing training time.