Metraipolis › archive › dc_bf01ea2ec316

Radial Kernel Attention for Long-Range Modeling in Polymer Machine Learning Force Fields — arXiv:2610.41675

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41675
License (as archived): CC0-1.0
Archived: 2026-11-02T07:19:08.001Z
SHA-256 of the archived text: 419c277741a26189e379d316c78513906d40eef13c9f65f63c1b97f7db2b02a7
Stable URL of this page: https://metraipolis.com/documento/dc_bf01ea2ec316

How to cite

Radial Kernel Attention for Long-Range Modeling in Polymer Machine Learning Force Fields — arXiv:2610.41675 — arXiv (en), https://arxiv.org/abs/2610.41675 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf01ea2ec316 (Metraipolis archive dc_bf01ea2ec316, sha256 419c277741a26189e379d316c78513906d40eef13c9f65f63c1b97f7db2b02a7)

BibTeX

@misc{dcbf01ea2ec316,
  title = {Radial Kernel Attention for Long-Range Modeling in Polymer Machine Learning Force Fields — arXiv:2610.41675},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41675},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf01ea2ec316; sha256 419c277741a26189e379d316c78513906d40eef13c9f65f63c1b97f7db2b02a7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41675. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce Radial Kernel Attention (RKA) for long-range modeling in polymer machine learning force fields. Local neighbor graphs constrain communication across polymer chains and their surrounding environments, while explicit all-pair attention incurs quadratic cost. RKA maps atomic distances from the cluster centroid to learned radial features and combines their overlap with content-dependent queries and keys. Factorized aggregation and readout enable global feature exchange at linear cost in atom count for fixed feature dimensions. We insert the invariant scalar update between EquiformerV3 local blocks and obtain conservative forces by differentiating the total energy, including its radial coordinate dependence. We evaluate energy and force prediction for finite polymer-derived clusters in OPoly26. Our models are trained on the official training split for 12 epochs and evaluated directly after training on the complete official validation split. A matched 5M comparison shows that RKA reduces per-atom energy and force MAEs by 67.4% and 36.3%, respectively. The 20M RKA model is compared with UMA-S-1.2 and UMA-S-1.2.1 on the same validation structures. The 20M model attains a total-energy MAE of 15.81 meV and a force MAE of 2.619 meV/angstrom; its per-atom energy MAE is 0.1182 meV/atom. RKA provides a compact global communication pathway that improves energy and force prediction on the evaluated polymer-derived clusters.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41675 — 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 2026-11-02T07:16:57.186Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).