Heterogeneous Graph Neural Networks for Malicious Account Detection

by   Ziqi Liu, et al.
Ant Financial
Georgia Institute of Technology

We present, GEM, the first heterogeneous graph neural network approach for detecting malicious accounts at Alipay, one of the world's leading mobile cashless payment platform. Our approach, inspired from a connected subgraph approach, adaptively learns discriminative embeddings from heterogeneous account-device graphs based on two fundamental weaknesses of attackers, i.e. device aggregation and activity aggregation. For the heterogeneous graph consists of various types of nodes, we propose an attention mechanism to learn the importance of different types of nodes, while using the sum operator for modeling the aggregation patterns of nodes in each type. Experiments show that our approaches consistently perform promising results compared with competitive methods over time.


page 1

page 2

page 3

page 4


HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning

Many real-world data can be represented as heterogeneous graphs with dif...

Heterogeneous Temporal Graph Neural Network

Graph neural networks (GNNs) have been broadly studied on dynamic graphs...

Suspicious Massive Registration Detection via Dynamic Heterogeneous Graph Neural Networks

Massive account registration has raised concerns on risk management in e...

Robust Hierarchical Graph Classification with Subgraph Attention

Graph neural networks get significant attention for graph representation...

Simple and Efficient Heterogeneous Graph Neural Network

Heterogeneous graph neural networks (HGNNs) deliver the powerful capabil...

Discriminative structural graph classification

This paper focuses on the discrimination capacity of aggregation functio...

Please sign up or login with your details

Forgot password? Click here to reset