Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.16901 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917964544999424 |
|---|---|
| author | Gounoue, Steve Sao, Ashutosh Gottschalk, Simon |
| author_facet | Gounoue, Steve Sao, Ashutosh Gottschalk, Simon |
| contents | Transaction graphs, which represent financial and trade transactions between entities such as bank accounts and companies, can reveal patterns indicative of financial crimes like money laundering and fraud. However, effective detection of such cases requires node and edge classification methods capable of addressing the unique challenges of transaction graphs, including rich edge features, multigraph structures and temporal dynamics. To tackle these challenges, we propose TeMP-TraG, a novel graph neural network mechanism that incorporates temporal dynamics into message passing. TeMP-TraG prioritises more recent transactions when aggregating node messages, enabling better detection of time-sensitive patterns. We demonstrate that TeMP-TraG improves four state-of-the-art graph neural networks by 6.19% on average. Our results highlight TeMP-TraG as an advancement in leveraging transaction graphs to combat financial crime. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16901 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TeMP-TraG: Edge-based Temporal Message Passing in Transaction Graphs Gounoue, Steve Sao, Ashutosh Gottschalk, Simon Machine Learning Transaction graphs, which represent financial and trade transactions between entities such as bank accounts and companies, can reveal patterns indicative of financial crimes like money laundering and fraud. However, effective detection of such cases requires node and edge classification methods capable of addressing the unique challenges of transaction graphs, including rich edge features, multigraph structures and temporal dynamics. To tackle these challenges, we propose TeMP-TraG, a novel graph neural network mechanism that incorporates temporal dynamics into message passing. TeMP-TraG prioritises more recent transactions when aggregating node messages, enabling better detection of time-sensitive patterns. We demonstrate that TeMP-TraG improves four state-of-the-art graph neural networks by 6.19% on average. Our results highlight TeMP-TraG as an advancement in leveraging transaction graphs to combat financial crime. |
| title | TeMP-TraG: Edge-based Temporal Message Passing in Transaction Graphs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.16901 |