RAGFormer: Learning Semantic Attributes and Topological Structure for Fraud Detection

2024-02-27

AI Summary

Fraud detection faces the challenge of jointly modeling semantic attributes and topological structural features. Existing methods typically rely on single-view representations, resulting in incomplete feature characterization. To address this, we propose the first unified framework that jointly encodes node semantics and graph topology. Our approach introduces a novel collaborative architecture comprising a relation-aware Graph Neural Network (GNN) and a multi-relation Transformer, integrated via a cross-feature dynamic attention mechanism that enables positive complementarity and adaptive fusion of semantic and structural features. Extensive experiments on multiple public benchmark datasets achieve state-of-the-art performance. Moreover, on an industrial-scale credit card fraud dataset, our method significantly improves both F1-score and AUC, demonstrating its effectiveness and practical applicability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Fraud detection remains a challenging task due to the complex and deceptive nature of fraudulent activities. Current approaches primarily concentrate on learning only one perspective of the graph: either the topological structure of the graph or the attributes of individual nodes. However, we conduct empirical studies to reveal that these two types of features, while nearly orthogonal, are each independently effective. As a result, previous methods can not fully capture the comprehensive characteristics of the fraud graph. To address this dilemma, we present a novel framework called Relation-Aware GNN with transFormer~(RAGFormer) which simultaneously embeds both semantic and topological features into a target node. The simple yet effective network consists of a semantic encoder, a topology encoder, and an attention fusion module. The semantic encoder utilizes Transformer to learn semantic features and node interactions across different relations. We introduce Relation-Aware GNN as the topology encoder to learn topological features and node interactions within each relation. These two complementary features are interleaved through an attention fusion module to support prediction by both orthogonal features. Extensive experiments on two popular public datasets demonstrate that RAGFormer achieves state-of-the-art performance. The significant improvement of RAGFormer in an industrial credit card fraud detection dataset further validates the applicability of our method in real-world business scenarios.

Problem

• Fraud detection complexity
• Semantic and topological integration
• State-of-the-art performance achievement

Innovation

• Combines semantic and topological features
• Uses Transformer for semantic encoding
• Integrates Relation-Aware GNN topology