Metraipolis › archive › dc_09ea150c5b08

TB-Transolver: Parallelized and Coherent Long-Horizon Rollouts via Temporal Bundling for Time-Dependent PDEs — arXiv:2611.04063

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04063
License (as archived)
CC0-1.0
Archived
2026-11-04T21:50:57.765Z
SHA-256 of the archived text
633af0dd3605df7254f2b3276669feea7d15cbb62b473d4d493b57af1eee27d3
Stable URL of this page
https://metraipolis.com/documento/dc_09ea150c5b08

How to cite

TB-Transolver: Parallelized and Coherent Long-Horizon Rollouts via Temporal Bundling for Time-Dependent PDEs — arXiv:2611.04063 — arXiv (en), https://arxiv.org/abs/2611.04063 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09ea150c5b08 (Metraipolis archive dc_09ea150c5b08, sha256 633af0dd3605df7254f2b3276669feea7d15cbb62b473d4d493b57af1eee27d3)
BibTeX
@misc{dc09ea150c5b08,
  title = {TB-Transolver: Parallelized and Coherent Long-Horizon Rollouts via Temporal Bundling for Time-Dependent PDEs — arXiv:2611.04063},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04063},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09ea150c5b08; sha256 633af0dd3605df7254f2b3276669feea7d15cbb62b473d4d493b57af1eee27d3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04063. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Transolver has recently gained widespread adoption for solving diverse physical problems on unstructured geometric meshes by leveraging its Physics-Attention mechanism, which seamlessly extends standard softmax attention to handle physical domains at scale. For time-dependent problems, existing literature relies on time-conditioned or autoregressive rollouts to preserve temporal causality while retaining Physics-Attention as the spatial backbone. However, a fundamental limitation of this formulation is its sequential execution model, wherein computational costs scale linearly with the temporal horizon, rendering standard Transolver inefficient for transient problems despite its exceptional spatial efficacy. This bottleneck has historically hindered its broader application in time-dependent physical modeling. To address this limitation, we introduce TB-Transolver (also referred to as Temporally Bundled Transolver), an efficient framework built on temporal bundling that scales Transolver for time-dependent PDEs. Furthermore, we propose \emph{spatiotemporal coherence} (${\rm C(K)}$) as a general metric to systematically quantify snapshot correlation within a temporal bundle, enabling the \emph{a priori} selection of optimal bundle widths using training data alone, thereby avoiding expensive grid searches. We demonstrate the computational efficacy of TB-Transolver across four physically distinct domains, namely, plasticity, fluid dynamics, reaction-diffusion, and global weather forecasting; achieving training speedups of up to $29\times$ over conventional autoregressive and time-conditioned baselines. Finally, these computational gains are further amplified through distributed multi-node and multi-GPU parallelism, yielding aggregated speedups of up to $45.6\times$ at optimal bundle widths for systems exhibiting high spatiotemporal coherence compared to single-GPU implementations.

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/2611.04063 — 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 2026-11-04T21:38:49.694Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).