EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Rotation-equivariant graph neural networks for learning glassy liquids representations

Francesco Saverio Pezzicoli, Guillaume Charpiat, François Pascal Landes

SciPost Physics · 28.05.2024 · 16 (5)

DOI: 10.21468/scipostphys.16.5.136 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SciPost Physics, online erschienen am 28.05.2024. Verfasst von Francesco Saverio Pezzicoli und 2 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agence Nationale de la Recherche, Grand Équipement National De Calcul Intensif.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The difficult problem of relating the static structure of glassy liquids and their dynamics is a good target for Machine Learning, an approach which excels at finding complex patterns hidden in data. Indeed, this approach is currently a hot topic in the glassy liquids community, where the state of the art consists in Graph Neural Networks (GNNs), which have great expressive power but are heavy models and lack interpretability. Inspired by recent advances in the field of Machine Learning group-equivariant representations, we build a GNN that learns a robust representation of the glass’ static structure by constraining it to preserve the roto-translation (SE(3)) equivariance. We show that this constraint significantly improves the predictive power at comparable or reduced number of parameters but most importantly, improves the ability to generalize to unseen temperatures. While remaining a Deep network, our model has improved interpretability compared to other GNNs, as the action of our basic convolution layer relates directly to well-known rotation-invariant expert features. Through transfer-learning experiments displaying unprecedented performance, we demonstrate that our network learns a robust representation, which allows us to push forward the idea of a learned structural order parameter for glasses.

Förderung

  • Agence Nationale de la Recherche
  • Grand Équipement National De Calcul Intensif

Zitieren

APA

Pezzicoli, F. S., Charpiat, G., & Landes, F. P. (2024). Rotation-equivariant graph neural networks for learning glassy liquids representations. SciPost Physics, 16(5). https://doi.org/10.21468/scipostphys.16.5.136

Vancouver

Pezzicoli FS, Charpiat G, Landes FP. Rotation-equivariant graph neural networks for learning glassy liquids representations. SciPost Physics. 2024;16(5). doi:10.21468/scipostphys.16.5.136

BibTeX
@article{Pezzicoli2024,
  author = {Pezzicoli, Francesco Saverio and Charpiat, Guillaume and Landes, François Pascal},
  title = {Rotation-equivariant graph neural networks for learning glassy liquids representations},
  journal = {SciPost Physics},
  year = {2024},
  volume = {16},
  number = {5},
  doi = {10.21468/scipostphys.16.5.136}
}
Kostenlos starten →