Dynamic Relation-Attentive Graph Neural Networks for Fraud Detection. (arXiv:2310.04171v1 [cs.LG])

Fraud detection aims to discover fraudsters deceiving other users by, for
example, leaving fake reviews or making abnormal transactions. Graph-based
fraud detection methods consider this task as a classification problem with two
classes: frauds or normal. We address this problem using Graph Neural Networks
(GNNs) by proposing a dynamic relation-attentive aggregation mechanism. Based
on the observation that many real-world graphs include different types of
relations, we propose to learn a node representation per relation and aggregate
the node representations using …

address classification detection discover dynamic fake fake reviews fraud fraud detection fraudsters graph making networks neural networks normal problem reviews task transactions