Label Information Enhanced Fraud Detection against Low Homophily in Graphs

TL;DR

This paper introduces GAGA, a novel transformer-based method that effectively utilizes label information and group aggregation to improve fraud detection in low homophily graphs, outperforming existing methods.

Contribution

The paper proposes GAGA, a new model combining group aggregation and learnable encodings within a Transformer to address low homophily challenges in graph-based fraud detection.

Findings

GAGA outperforms other methods by up to 24.39% on public and industrial datasets.

Group aggregation surpasses other label utilization techniques in low homophily settings.

The model effectively captures semantic, structural, and relational information for improved detection.

Abstract

Node classification is a substantial problem in graph-based fraud detection. Many existing works adopt Graph Neural Networks (GNNs) to enhance fraud detectors. While promising, currently most GNN-based fraud detectors fail to generalize to the low homophily setting. Besides, label utilization has been proved to be significant factor for node classification problem. But we find they are less effective in fraud detection tasks due to the low homophily in graphs. In this work, we propose GAGA, a novel Group AGgregation enhanced TrAnsformer, to tackle the above challenges. Specifically, the group aggregation provides a portable method to cope with the low homophily issue. Such an aggregation explicitly integrates the label information to generate distinguishable neighborhood information. Along with group aggregation, an attempt towards end-to-end trainable group encoding is proposed which augments the original feature space with the class labels. Meanwhile, we devise two additional learnable encodings to recognize the structural and relational context. Then, we combine the group aggregation and the learnable encodings into a Transformer encoder to capture the semantic information. Experimental results clearly show that GAGA outperforms other competitive graph-based fraud detectors by up to 24.39% on two trending public datasets and a real-world industrial dataset from Anonymous. Even more, the group aggregation is demonstrated to outperform other label utilization methods (e.g., C&S, BoT/UniMP) in the low homophily setting.