Metraipolis › archive › dc_3218fd72f66f

PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs — arXiv:2609.34715

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34715
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:06.307Z
SHA-256 of the archived text
b793c07f779b4a96c3b810b61e405233b5b8584b32e39ec27fc9a82f0593f546
Stable URL of this page
https://metraipolis.com/documento/dc_3218fd72f66f

How to cite

PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs — arXiv:2609.34715 — arXiv (en), https://arxiv.org/abs/2609.34715 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3218fd72f66f (Metraipolis archive dc_3218fd72f66f, sha256 b793c07f779b4a96c3b810b61e405233b5b8584b32e39ec27fc9a82f0593f546)
BibTeX
@misc{dc3218fd72f66f,
  title = {PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs — arXiv:2609.34715},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34715},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3218fd72f66f; sha256 b793c07f779b4a96c3b810b61e405233b5b8584b32e39ec27fc9a82f0593f546},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34715. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physical trajectories contain more than snapshots of a system: they also reveal how its states evolve under governing conditions. However, representation learning for parametric partial differential equations (PDEs) has largely relied on reconstruction-based objectives that emphasize recovering observed physical fields. In this paper, we investigate predictive representation pretraining as an alternative to reconstruction-based learning. We find that predictive representations preserve rich physical information, yet this advantage alone does not ensure accurate field evolution. Based on these observations, we introduce PDE-JEPA for parametric PDE dynamics. Specifically, we first train an encoder using a masked-latent prediction to capture the underlying regularities of PDE dynamics. To explicitly adapt the pretrained representation toward a more dynamics-aligned state space, we then introduce a geometry projector that aligns latent trajectory geometry with the evolution geometry of physical fields. Finally, building on this geometry-aligned latent space, we further develop a physics-structured latent predictor that decomposes the dynamics into parameter-independent evolution and parameter-dependent response components. Extensive experiments on nine widely used PDE benchmarks demonstrate that our framework outperforms existing state-of-the-art methods by an average of 33.4\% in-distribution, while achieving an average improvement of 51.4\% when extrapolating to unseen governing parameters. The project page is available \href{ this https URL }{here}.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34715 — 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 2026-10-07T20:29:01.640Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).