Metraipolis › archive › dc_7fe95984c780
Rethinking Cross-Channel Importance in Time-Series Forecasting — arXiv:2609.32187
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32187
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:36:20.142Z
- SHA-256 of the archived text
525abc32750a04b258df433e36911be5a74b2deec18d832c41b32253f773fefb- Stable URL of this page
https://metraipolis.com/documento/dc_7fe95984c780
How to cite
Rethinking Cross-Channel Importance in Time-Series Forecasting — arXiv:2609.32187 — arXiv (en), https://arxiv.org/abs/2609.32187 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fe95984c780 (Metraipolis archive dc_7fe95984c780, sha256 525abc32750a04b258df433e36911be5a74b2deec18d832c41b32253f773fefb)
BibTeX
@misc{dc7fe95984c780,
title = {Rethinking Cross-Channel Importance in Time-Series Forecasting — arXiv:2609.32187},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32187},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fe95984c780; sha256 525abc32750a04b258df433e36911be5a74b2deec18d832c41b32253f773fefb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32187. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Cross-channel modeling is central to multivariate time-series forecasting, yet channels that are statistically related, predictively useful, and actually used by a trained forecaster are often treated as if they defined the same notion of importance. We show that they need not coincide. Cross-channel dependency structures change substantially across future offsets, and horizon-adaptive source selection improves a controlled Ridge predictor in 21 of 32 dataset--prediction-length conditions, with a mean gain of $5.16\%$. This selected-set signal also transfers to a matched nonlinear predictor. Yet imposing the same horizon-specific source logic on iTransformer yields only 11 of 20 wins and a mean gain of $0.208\%$, with little alignment between controlled and neural gains. Functional interventions further show that strong forecasters use cross-channel information, while their source-reliance rankings agree little with controlled utility or with one another across iTransformer, TimesNet, and a cross-channel TimeMixer. As a constructive consequence, bounded post-hoc support improves a frozen channel-independent forecaster in 12 of 16 dataset--horizon conditions, with a positive aggregate bootstrap interval. Cross-channel importance should therefore be interpreted relative to the forecasting mechanism and question that define it: related $\neq$ useful $\neq$ used. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.32187 — 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 2026-10-07T22:14:27.612Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).