Metraipolis › archive › dc_a0b62d116fef

ZeoBench: A Benchmark for Self-Supervised Learning on 3D Zeolite Representations — arXiv:2611.09880

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09880
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:30.551Z
SHA-256 of the archived text
f8c32c7131be4f1daf125cd499d1f13eadc6b8ea877c88c4f68ad34b96d4fec4
Stable URL of this page
https://metraipolis.com/documento/dc_a0b62d116fef

How to cite

ZeoBench: A Benchmark for Self-Supervised Learning on 3D Zeolite Representations — arXiv:2611.09880 — arXiv (en), https://arxiv.org/abs/2611.09880 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0b62d116fef (Metraipolis archive dc_a0b62d116fef, sha256 f8c32c7131be4f1daf125cd499d1f13eadc6b8ea877c88c4f68ad34b96d4fec4)
BibTeX
@misc{dca0b62d116fef,
  title = {ZeoBench: A Benchmark for Self-Supervised Learning on 3D Zeolite Representations — arXiv:2611.09880},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09880},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0b62d116fef; sha256 f8c32c7131be4f1daf125cd499d1f13eadc6b8ea877c88c4f68ad34b96d4fec4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09880. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Zeolites are an important class of porous crystalline materials with broad applications in gas storage, separations, and catalysis. Although hundreds of thousands of experimentally realized and hypothetical zeolite structures are known, identifying materials optimized for a target application remains challenging because property labels are expensive to obtain and available only for limited structure-molecule pairs. While prior work has demonstrated that 3D neural representations can predict zeolite properties effectively, it remains unclear which representation-learning strategies are most effective in the low-data regime relevant to materials discovery. We present ZeoBench, a benchmark for self-supervised learning on dense 3D representations of all-silica zeolites, and evaluate the resulting features on six existing downstream adsorption-property prediction tasks, across a range of training set sizes. Our study compares self-supervised 3D pretraining on volumetric zeolite data, adaptations of image-pretrained 2D ConvNets and vision transformers to 3D via multiview and channel-inflation strategies, and 3D ConvNets pretrained on out-of-domain volumetric datasets, alongside hand-crafted descriptors and supervised baselines. Using our pretraining and evaluation framework, we find self-supervised 3D representations outperform existing methods and achieve state-of-the-art performance across both in-domain label regimes and for the unseen domain of metal organic frameworks. Learned representations consistently outperform hand-crafted descriptors, and convolutional architectures are generally more effective than vision transformers in this setting. These results establish ZeoBench as a practical benchmark for 3D representation learning in zeolites and provide guidance for data-limited adsorption property prediction.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.09880 — 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 2026-11-09T22:37:47.236Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).