Metraipolis › archive › dc_4d236126ffc5

Temporal Graph Prototype-conditioned Conformal Prediction for Fraud Detection — arXiv:2608.15768

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15768
License (as archived)
CC0-1.0
Archived
2026-10-18T18:04:25.411Z
SHA-256 of the archived text
f216a9827a07d8f346f8289f2c871d1c9df60d6ac0a68b3c3a355e12dbca38a0
Stable URL of this page
https://metraipolis.com/documento/dc_4d236126ffc5

How to cite

Temporal Graph Prototype-conditioned Conformal Prediction for Fraud Detection — arXiv:2608.15768 — arXiv (en), https://arxiv.org/abs/2608.15768 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d236126ffc5 (Metraipolis archive dc_4d236126ffc5, sha256 f216a9827a07d8f346f8289f2c871d1c9df60d6ac0a68b3c3a355e12dbca38a0)
BibTeX
@misc{dc4d236126ffc5,
  title = {Temporal Graph Prototype-conditioned Conformal Prediction for Fraud Detection — arXiv:2608.15768},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15768},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d236126ffc5; sha256 f216a9827a07d8f346f8289f2c871d1c9df60d6ac0a68b3c3a355e12dbca38a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15768. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conformal prediction (CP) provides distribution-free coverage guarantees and has emerged as a principled tool for uncertainty quantification. In edge-level fraud detection on temporal interaction graphs, where false positives and false negatives both carry substantial cost, such coverage guarantees are particularly appealing for risk-aware decision making. However, directly applying existing graph conformal predictors yields inefficient prediction sets due to two recurring properties of fraud data. Fraudulent interactions are often embedded in benign-dominated neighborhoods that dilute calibration signals, while extreme class imbalance leaves scarce labeled-fraud support in the calibration split and leads to overly conservative class-conditional thresholds. To address these issues, we propose ProtoCP, a conformal prediction framework for edge-level fraud detection on temporal graphs. ProtoCP improves calibration efficiency by focusing calibration on fraud-relevant subgraph context and producing more stable nonconformity scores under class imbalance and temporal drift. Specifically, it leverages learned prototypes to suppress benign-dominated noise in the calibration context and introduces a neighborhood-relative scoring mechanism with temporal score diffusion for stable class-conditional calibration. Experiments on four fraud benchmarks (YelpChi, S-FFSD, FTFD, and BankSim) show that ProtoCP achieves the target coverage with consistently smaller prediction sets than state-of-the-art baselines. Our codes are available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15768 — 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 2026-10-18T16:29:14.049Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).