Metraipolis › archive › dc_ce5ba65a982b
LLM-Enhanced Heterogeneous Graph Learning with Business Semantics for Financial Fraud Detection — arXiv:2610.35298
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.35298
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:58:33.413Z
- SHA-256 of the archived text
6e061ce0b5ff2993cc3444b56024351421ea6a9159dc4dd0ace4079d217e45b0- Stable URL of this page
https://metraipolis.com/documento/dc_ce5ba65a982b
How to cite
LLM-Enhanced Heterogeneous Graph Learning with Business Semantics for Financial Fraud Detection — arXiv:2610.35298 — arXiv (en), https://arxiv.org/abs/2610.35298 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce5ba65a982b (Metraipolis archive dc_ce5ba65a982b, sha256 6e061ce0b5ff2993cc3444b56024351421ea6a9159dc4dd0ace4079d217e45b0)
BibTeX
@misc{dcce5ba65a982b,
title = {LLM-Enhanced Heterogeneous Graph Learning with Business Semantics for Financial Fraud Detection — arXiv:2610.35298},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.35298},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce5ba65a982b; sha256 6e061ce0b5ff2993cc3444b56024351421ea6a9159dc4dd0ace4079d217e45b0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35298. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Financial fraud detection increasingly relies on heterogeneous transaction graphs, in which entities such as cards and merchants play distinct business roles and the risk meaning of an attribute depends on the entity's role: a high transaction volume may be routine for a merchant but unusual for a card. Heterogeneous graph neural networks preserve typed entities and relations but typically treat these attributes as role-agnostic inputs and leave their business meaning implicit. Meanwhile, most existing methods integrating large language models (LLMs) with graphs focus on homogeneous graphs or heterogeneous graphs with naturally available textual attributes, leaving their use on transaction graphs with structured attributes underexplored. To address this issue, we propose SemHGT, an LLM-enhanced framework that interprets structured attributes according to entity roles and makes the business semantics explicit in three stages: (1) role-aware prompts elicit risk-related business descriptions from node attributes, and a text encoder maps them to semantic vectors that enrich node representations; (2) semantic similarity guides multi-round sampling of target-specific path instances under transaction-to-transaction schemas; (3) schema-level tokens that combine local path evidence with global neighbor summaries are processed together with the target transaction by a unified transformer. Across three benchmark datasets, SemHGT leads the evaluated baselines on most dataset--metric comparisons. Further analyses provide additional evidence for the effectiveness of SemHGT's design and clarify how its semantic modeling and evidence selection contribute to fraud detection. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.35298 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-27T07:55:30.748Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).