Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection

By Zhiwei Liu, Yingtong Dou, Philip S. Yu, Yutong Deng. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020

383 citations recorded by the source corpus.

Graph-based models have been widely used to fraud detection tasks. Owing to the development of Graph Neural Networks~(GNNs), recent works have proposed many GNN-based fraud detectors based on either homogeneous or heterogeneous graphs. These works leverage existing GNNs and aggregate the neighborhood information to learn the node embeddings, which relies on the assumption that the neighbors share similar context, features, and relations. However, the inconsistency problem incurred by fraudsters is hardly investigated, i.e., the context inconsistency, feature inconsistency, and relation inconsistency. In this paper, we introduce these inconsistencies and design a new GNN framework, GraphConsis, to tackle the inconsistency problem: (1) for the context inconsistency, we propose to combine the context embeddings with node features; (2) for the feature inconsistency, we design a consistency score to filter the inconsistent neighbors and generate corresponding sampling probability; (3) for the relation inconsistency, we learn the relation attention weights associated with the sampled nodes. Empirical analysis on four datasets demonstrates that the inconsistency problem is critical in fraud detection tasks. Extensive experiments show the effectiveness of GraphConsis. We also released a GNN-based fraud detection toolbox with implementations of SOTA models. The code is available at \urlhttps://github.com/safe-graph/DGFraud

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/8cf8e7fe56f26e9e811cf409e1ceeb7c9d7fb60b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hui Xiong
2. Qing He
3. Chuan Zhou
4. Jia Wu
5. Quan Z. Sheng
6. Shan Xue
7. Jian Yang
8. Jia Li

In Information Systems

1. Hui Xiong
2. Jia Wu
3. Qing He
4. Zi-Chao Gao
5. Philip S. Yu
6. Yutong Deng
7. Quan Z. Sheng
8. Hao Peng

Citations in the corpus

• A Comprehensive Survey on Graph Anomaly Detection With Deep Learning (2021, methodology): “com/YingtongDou/CARE-GNN GraphConsis [128] Python Tensorflow Static Attributed Graph https://github.”
• Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection (2021, background): “• GraphConsis [26]: a heterogeneous graph neural network which tackles context inconsistency, feature inconsistency and relation inconsistency problem.”
• Rethinking Graph Neural Networks for Anomaly Detection (2022, methodology): “We choose two widely used datasets in previous works (Liu et al., 2021b; 2020), including the Amazon dataset (McAuley & Leskovec, 2013) for user anomaly detection and the YelpChi dataset (Rayana & Akoglu, 2015) for review anomaly detection.”
• Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters (2020, methodology): “Though some recent works [4, 9, 13, 25, 41] have noticed similar challenges, their solutions either fail to fit the fraud detection problems or break the end-to-end learning fashion of GNNs.”