Metraipolis › archive › dc_b74a256e7ff0
A Hybrid Attention Model Learning Unified Time-aware Patch Representation for Irregular Multivariate Time Series Forecasting — arXiv:2609.22836
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22836
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T07:06:51.744Z
- SHA-256 of the archived text
1ea31ca716d510525bd144b5b3ee48e5325f47bb4b8c4dc8628453e7a0a22c3a- Stable URL of this page
https://metraipolis.com/documento/dc_b74a256e7ff0
How to cite
A Hybrid Attention Model Learning Unified Time-aware Patch Representation for Irregular Multivariate Time Series Forecasting — arXiv:2609.22836 — arXiv (en), https://arxiv.org/abs/2609.22836 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b74a256e7ff0 (Metraipolis archive dc_b74a256e7ff0, sha256 1ea31ca716d510525bd144b5b3ee48e5325f47bb4b8c4dc8628453e7a0a22c3a)
BibTeX
@misc{dcb74a256e7ff0,
title = {A Hybrid Attention Model Learning Unified Time-aware Patch Representation for Irregular Multivariate Time Series Forecasting — arXiv:2609.22836},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22836},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b74a256e7ff0; sha256 1ea31ca716d510525bd144b5b3ee48e5325f47bb4b8c4dc8628453e7a0a22c3a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22836. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Time series foundation models (TSFMs) have recently delivered impressive zero-shot performance across diverse forecasting tasks. However, real-world decision-making frequently relies on \emph{irregular multivariate time series} (IMTS), where inconsistent inter-observation intervals and asynchronous sampling across variables coexist with informative missingness. Existing TSFMs handle such inputs either through imputation that injects spurious values or through index-based positional encodings that ignore continuous time. There is still a gap in the foundation model that follows the original IMTS patterns. In this paper, we propose a hybrid attention model that learns a unified time-aware patch representation for IMTS forecasting. We first design a \emph{time-aware patch encoding} that maps a variable number of intra-patch timestamps into a fixed-size embedding, producing a uniform format for irregular patches without resorting to imputation. We then introduce a \emph{time bias attention} mechanism that calibrates inter-patch temporal misalignment and asynchronous cross-channel dependencies as auxiliary attention offset. Finally, on top of a decoder-only Transformer backbone, we adopt a \emph{hybrid causal mask} that preserves a bidirectional full view over the historical context while keeping the forecast horizon strictly autoregressive. To support large-scale pretraining under irregular settings, we also curate VersaTSA, an archive of $30$B observations that retains the native sampling sparsity of its sources. Experiments on three IMTS benchmarks and a standard regular-MTS benchmark show that our model achieves state-of-the-art zero-shot performance on IMTS and remains competitive when transferred to regular forecasting.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.22836 — 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 2026-10-09T06:58:09.230Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).