April 22 - 26, 2024
Seattle, Washington
May 7 - 9, 2024 (Virtual)
Symposium Supporters
2024 MRS Spring Meeting
MT01.09.04

Adaptive Loss Weighting for Machine Learning Interatomic Potentials

When and Where

Apr 25, 2024
5:00pm - 7:00pm
Flex Hall C, Level 2, Summit

Presenter(s)

Co-Author(s)

Daniel Ocampo1,Daniela Posso2,Reza Namakian1,Wei Gao1

Texas A&M University1,The University of Texas at San Antonio2

Abstract

Daniel Ocampo1,Daniela Posso2,Reza Namakian1,Wei Gao1

Texas A&M University1,The University of Texas at San Antonio2
For atomistic simulations, machine learning interatomic potentials (ML-IAPs) have proven to accurately represent potential energy surfaces, overcoming some limitations of empirical force-fields and their functional form. Training such potentials involves optimization of multipart loss functions typically composed of potential energies, forces and stress tensors. However, the contribution of each variable to the total loss is typically weighted using heuristic approaches that yield either iterative or sub-optimal results. Therefore, we implement an adaptive loss weighting algorithm based on a mathematically intuitive and computationally efficient scheme, in which the contribution of each term is dynamically recalculated based on its learning performance; optimizing the imbalance of the widely used, heuristic fixed loss weighting approaches. Additionally, by adding a stress term to the loss function and using high convergence criteria for density functional theory (DFT) calculations we show that a ML-IAP with accurate predictive stress capabilities must include stress information during training. This approach results in more automated neural networks networks that can learn effectively potential energies, forces and stresses from <i>ab initio</i> calculations, producing reliable ML-IAPs that are usable in simulations involving mechanical deformations, phase transformations, or other stress-dependent phenomena.

Symposium Organizers

Raymundo Arroyave, Texas A&M Univ
Elif Ertekin, University of Illinois at Urbana-Champaign
Rodrigo Freitas, Massachusetts Institute of Technology
Aditi Krishnapriyan, UC Berkeley

Session Chairs

Chris Bartel
Rodrigo Freitas
Sara Kadkhodaei
Wenhao Sun

In this Session