Metraipolis › archive › dc_9825a2bc06ff

DISTAL: Distillation and Self-Supervised Pretraining for Structure-Agnostic Materials Property Prediction — arXiv:2609.00059

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00059
License (as archived): CC0-1.0
Archived: 2026-10-17T06:32:38.185Z
SHA-256 of the archived text: 2f4b81138a7b0c577f632fbd64eee88a8c8403a33649b32b9d5107f5f10cb460
Stable URL of this page: https://metraipolis.com/documento/dc_9825a2bc06ff

How to cite

DISTAL: Distillation and Self-Supervised Pretraining for Structure-Agnostic Materials Property Prediction — arXiv:2609.00059 — arXiv (en), https://arxiv.org/abs/2609.00059 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9825a2bc06ff (Metraipolis archive dc_9825a2bc06ff, sha256 2f4b81138a7b0c577f632fbd64eee88a8c8403a33649b32b9d5107f5f10cb460)

BibTeX

@misc{dc9825a2bc06ff,
  title = {DISTAL: Distillation and Self-Supervised Pretraining for Structure-Agnostic Materials Property Prediction — arXiv:2609.00059},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00059},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9825a2bc06ff; sha256 2f4b81138a7b0c577f632fbd64eee88a8c8403a33649b32b9d5107f5f10cb460},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00059. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Materials property prediction remains difficult in low-data settings, where many target properties are supported by only a limited number of labeled samples. Models with the strongest predictive accuracy often depend on crystal structures, which restricts their use in early-stage screening when structural information is limited or unavailable. To address this challenge, we propose DISTAL, a dual-prior framework for structure-agnostic materials property prediction that combines self-supervised compositional pretraining with structure-aware knowledge distillation. DISTAL first learns transferable compositional representations from a large virtual composition space using 145 composition-derived descriptors. It then distills structural knowledge from a pretrained ALIGNN teacher into a composition-conditioned student. This setting allows structural priors to be used during training without requiring structural inputs at inference. By integrating explicit compositional descriptors, pretrained latent features, and distilled structural features within a unified prediction pipeline, DISTAL captures complementary signals that are difficult to recover from any single representation alone. Across 39 benchmark tasks, the best-performing multimodal configuration combines all three signals, and improves over the reference benchmark on 37 tasks. DISTAL achieves the strongest overall performance among all evaluated feature combinations. These results indicate that compositional pretraining and structural distillation provide complementary priors and offer a practical route to robust composition-only prediction in small-data materials informatics. The source code and the pre-trained models are anonymously available at: this https URL and will be released at the official link after acceptance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET).
Pagina del lavoro: https://arxiv.org/abs/2609.00059 — 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 2026-10-17T06:15:12.722Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).