Metraipolis › archive › dc_b91faeee8e23
OmniST: Topology-Invariant Spatiotemporal Forecasting with Guaranteed-Coverage Uncertainty at Unseen Sensor Locations — arXiv:2611.04256
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04256
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:39:55.876Z
- SHA-256 of the archived text
3dacb8be6fd249d4a22133fb2a18d4e8ec7bbaf2699f7b6fd66fdacc9c6bfdb0- Stable URL of this page
https://metraipolis.com/documento/dc_b91faeee8e23
How to cite
OmniST: Topology-Invariant Spatiotemporal Forecasting with Guaranteed-Coverage Uncertainty at Unseen Sensor Locations — arXiv:2611.04256 — arXiv (en), https://arxiv.org/abs/2611.04256 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b91faeee8e23 (Metraipolis archive dc_b91faeee8e23, sha256 3dacb8be6fd249d4a22133fb2a18d4e8ec7bbaf2699f7b6fd66fdacc9c6bfdb0)
BibTeX
@misc{dcb91faeee8e23,
title = {OmniST: Topology-Invariant Spatiotemporal Forecasting with Guaranteed-Coverage Uncertainty at Unseen Sensor Locations — arXiv:2611.04256},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04256},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b91faeee8e23; sha256 3dacb8be6fd249d4a22133fb2a18d4e8ec7bbaf2699f7b6fd66fdacc9c6bfdb0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04256. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Standard spatiotemporal graph convolutional networks need a fixed-size adjacency matrix, coupling model weights to a specific sensor count N; they cannot produce any output at a sensor absent from training. We present OmniST, a topology-invariant forecaster whose computation has zero structural dependency on the number of nodes, and which, composed with inductive split-conformal calibration, gives distribution-free, coverage-guaranteed prediction intervals at arbitrary (including never-seen) sensor locations, preserving that guarantee as sensors are added or removed. Topology invariance follows from coordinate-based tokenization, k-nearest-neighbor attention from geographic coordinates at each forward pass, and per-node temporal processing via a bidirectional GRU. On real Delhi air-quality data (37 stations, 2019-2023), OmniST attains a 30-day PM2.5 MAE of 31.0 ug/m3 and degrades at most 1.1 percent when 40 percent of stations are removed. Its inductive forecasts at unseen stations beat nearest-neighbor interpolation (about 12 percent) and a learned kriging GNN (IGNNK, about 21 percent), and, unlike either, carry a finite-sample coverage guarantee. The guarantee holds at 90 percent or above under 30-50 percent node dropout across four real datasets over three domains (Delhi and Beijing air quality, NOAA GHCN weather, Caltrans PeMSD7-M traffic), and still holds at 325 real sensors (full PeMS-BAY). We also fix a temporal-drift failure: static conformal under-covers over time (about 0.50 late), but a rolling adaptive-conformal estimator restores target coverage (0.89 overall, 0.96 late) at the cost of wider intervals. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2611.04256 — 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 2026-11-04T21:35:49.656Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).