Metraipolis › archive › dc_3df7c5f4e4e4

RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction — arXiv:2608.20656

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.20656
License (as archived): CC0-1.0
Archived: 2026-10-18T10:31:01.395Z
SHA-256 of the archived text: 8a6c26ac1a74503278508edec12e7bda8d8962320044990da0fe13782c288c1d
Stable URL of this page: https://metraipolis.com/documento/dc_3df7c5f4e4e4

How to cite

RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction — arXiv:2608.20656 — arXiv (en), https://arxiv.org/abs/2608.20656 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3df7c5f4e4e4 (Metraipolis archive dc_3df7c5f4e4e4, sha256 8a6c26ac1a74503278508edec12e7bda8d8962320044990da0fe13782c288c1d)

BibTeX

@misc{dc3df7c5f4e4e4,
  title = {RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction — arXiv:2608.20656},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20656},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3df7c5f4e4e4; sha256 8a6c26ac1a74503278508edec12e7bda8d8962320044990da0fe13782c288c1d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20656. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Traffic sensors commonly record flow, speed, and occupancy, but standard traffic flow forecasting benchmarks and models rarely exploit all three raw measurements reliably. Although speed and occupancy provide sensor-native traffic-state information beyond flow alone, existing releases often omit these variables, replace them with proxies, or contain logically inconsistent records. Moreover, direct empirical risk minimization over three-variable inputs may exploit regime-dependent shortcuts, as the relationships among flow, speed, and occupancy vary substantially between free-flow and congested states. We introduce \textbf{PEMSB-3V}, a public benchmark suite that preserves raw flow, speed, and occupancy measurements from PeMS detectors for flow prediction. We also propose \textbf{RiskTraf}, a model-agnostic risk-extrapolated residual plug-in. For each trained spatio-temporal backbone, RiskTraf freezes the selected checkpoint and learns a lightweight zero-start residual head from historical speed and occupancy. The residual head constructs ordered traffic-risk environments and optimizes horizon-wise flow corrections with a risk extrapolation objective, thereby mitigating regime-specific shortcut correlations without modifying the backbone. Extensive experiments demonstrate that RiskTraf consistently improves diverse forecasting backbones and outperforms debiasing and distribution-shift adaptation methods. Our code and benchmark are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.20656 — 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 2026-10-18T10:27:55.934Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).