Metraipolis › archive › dc_0d4e5fa198dd

Structure-Aware Graph Abstention for Reliable Selective Forecasting — arXiv:2610.08322

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.08322
License (as archived): CC0-1.0
Archived: 2026-10-07T11:41:44.032Z
SHA-256 of the archived text: 34a65e001c10b16221b52db73429578af11396f6b4a331267fdf9746e9152b29
Stable URL of this page: https://metraipolis.com/documento/dc_0d4e5fa198dd

How to cite

Structure-Aware Graph Abstention for Reliable Selective Forecasting — arXiv:2610.08322 — arXiv (en), https://arxiv.org/abs/2610.08322 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d4e5fa198dd (Metraipolis archive dc_0d4e5fa198dd, sha256 34a65e001c10b16221b52db73429578af11396f6b4a331267fdf9746e9152b29)

BibTeX

@misc{dc0d4e5fa198dd,
  title = {Structure-Aware Graph Abstention for Reliable Selective Forecasting — arXiv:2610.08322},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08322},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d4e5fa198dd; sha256 34a65e001c10b16221b52db73429578af11396f6b4a331267fdf9746e9152b29},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08322. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Selective forecasting abstains on high-risk test windows under a retained-coverage budget. Existing gates such as TEM (Brusokas et al., 2025) score each forecast as a whole; for multivariate outputs, trajectories can look plausible while violating dependencies among variables. We treat instance-level plausibility and relational consistency as distinct reliability axes and operationalize the latter via a learned sparse graph and a Dirichlet-style structural energy E_struct, trained with error-weighted graph regularization and score-error alignment. On seven long-horizon benchmarks and four backbones, structural gating often reduces selective MSE versus TEM at matched coverage, with the largest gains where cross-variable structure appears more informative in our benchmarks; gains are not universal, indicating a complementary abstention signal. Table 1 is a Protocol A ranking diagnostic (seed 2024); three-seed deployable Protocol B on an aligned subset is in Table 3 (full validation-to-test grids: Appendix A).

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.08322 — 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 2026-10-07T11:19:24.824Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).