Equivariant Message Passing Neural Network for Crystal Material Discovery

التفاصيل البيبلوغرافية
العنوان: Equivariant Message Passing Neural Network for Crystal Material Discovery
المؤلفون: Klipfel, Astrid, Peltre, Olivier, Harrati, Najwa, Fregier, Yaël, Sayede, Adlane, Bouraoui, Zied
سنة النشر: 2023
المجموعة: Computer Science
مصطلحات موضوعية: Computer Science - Machine Learning
الوصف: 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.
نوع الوثيقة: Working Paper
URL الوصول: http://arxiv.org/abs/2302.00485
رقم الأكسشن: edsarx.2302.00485
قاعدة البيانات: arXiv