paper-with-me

홈 › Papers

Equivariant Message Passing Neural Network for Crystal Material Discovery

2023-02-01 · Astrid Klipfel, Olivier Peltre, Najwa Harrati, Yaël Fregier, Adlane Sayede, Zied Bouraoui

Automatic material discovery with desired properties is a fundamental challenge for material sciences. Considerable attention has recently been devoted to generating stable crystal structures. While existing work has shown impressive success on supervised tasks such as property prediction, the progress on unsupervised tasks such as material generation is still hampered by the limited extent to which the equivalent geometric representations of the same crystal are considered. To address this challenge, we propose EMPNN a periodic equivariant message-passing neural network that learns crystal lattice deformation in an unsupervised fashion. Our model equivalently acts on lattice according to the deformation action that must be performed, making it suitable for crystal generation, relaxation and optimisation. We present experimental evaluations that demonstrate the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2302.00485

Code (1)

aklipf/pegnn 공식 구현 pytorch

Tasks

Property Prediction

Similar Papers 제목 키워드 기반

Equivariant Networks for Crystal Structures

2022-11-15 · Sékou-Oumar Kaba, Siamak Ravanbakhsh

Supervised learning with deep models has tremendous potential for applications in materials science. Recently, graph neural networks have been used in this context, drawing direct inspiration from models for molecules. H…

Property Prediction

Open Materials Generation with Stochastic Interpolants

2025-02-04 · Philipp Hoellmer, Thomas Egg, Maya M. Martirossyan, Eric Fuemmeler 외

The discovery of new materials is essential for enabling technological advancements. Computational approaches for predicting novel materials must effectively learn the manifold of stable crystal structures within an infi…

A Materials Foundation Model via Hybrid Invariant-Equivariant Architectures

2025-02-25 · Keqiang Yan, Montgomery Bohde, Andrii Kryvenko, Ziyu Xiang 외

Machine learning interatomic potentials (MLIPs) can predict energy, force, and stress of materials and enable a wide range of downstream discovery tasks. A key design choice in MLIPs involves the trade-off between invari…

Computational Efficiency

Unified Model for Crystalline Material Generation

2023-06-07 · Astrid Klipfel, Yaël Frégier, Adlane Sayede, Zied Bouraoui

One of the greatest challenges facing our society is the discovery of new innovative crystal materials with specific properties. Recently, the problem of generating crystal materials has received increasing attention, ho…

model

Force-Free Molecular Dynamics Through Autoregressive Equivariant Networks

2025-03-31 · Fabian L. Thiemann, Thiago Reschützegger, Massimiliano Esposito, Tseden Taddese 외

Molecular dynamics (MD) simulations play a crucial role in scientific research. Yet their computational cost often limits the timescales and system sizes that can be explored. Most data-driven efforts have been focused o…

Numerical Integration