DyHDGE: Dynamic heterogeneous transaction graph embedding for safety-centric fraud detection in financial scenarios
Dynamic graph fraud detection aims to distinguish fraudulent entities that deviate significantly from most benign entities within an ever-changing graph network. However, when dealing with different financial fraud scenarios, existing methods face challenges, resulting in difficulty in effectively e...
Shranjeno v:
| Principais autores: | , , , |
|---|---|
| Format: | Artigo |
| Jezik: | Inglês |
| Izdano: |
KeAi Communications Co., Ltd.
2024-12-01
|
| Serija: | Journal of Safety Science and Resilience |
| Teme: | |
| Online dostop: | http://www.sciencedirect.com/science/article/pii/S2666449624000483 |
| Oznake: |
Brez oznak, prvi označite!
|