Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials

• URL: http://arxiv.org/abs/2502.03660v1
• Date: Wed, 05 Feb 2025 23:04:21 GMT
• Title: Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials
• Authors: Santiago Miret, Kin Long Kelvin Lee, Carmelo Gonzales, Sajid Mannan, N. M. Anoop Krishnan,
• Abstract summary: Universal Machine Learning Interactomic Potentials (MLIPs) enable accelerated simulations for materials discovery. MLIPs' inability to reliably and accurately perform large-scale molecular dynamics (MD) simulations for diverse materials.
• Score: 8.254607304215451
• License:
• Abstract: Universal Machine Learning Interactomic Potentials (MLIPs) enable accelerated simulations for materials discovery. However, current research efforts fail to impactfully utilize MLIPs due to: 1. Overreliance on Density Functional Theory (DFT) for MLIP training data creation; 2. MLIPs' inability to reliably and accurately perform large-scale molecular dynamics (MD) simulations for diverse materials; 3. Limited understanding of MLIPs' underlying capabilities. To address these shortcomings, we aargue that MLIP research efforts should prioritize: 1. Employing more accurate simulation methods for large-scale MLIP training data creation (e.g. Coupled Cluster Theory) that cover a wide range of materials design spaces; 2. Creating MLIP metrology tools that leverage large-scale benchmarking, visualization, and interpretability analyses to provide a deeper understanding of MLIPs' inner workings; 3. Developing computationally efficient MLIPs to execute MD simulations that accurately model a broad set of materials properties. Together, these interdisciplinary research directions can help further the real-world application of MLIPs to accurately model complex materials at device scale.

Related papers

• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [70.91804882618243]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks. We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge. Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• Global Universal Scaling and Ultra-Small Parameterization in Machine Learning Interatomic Potentials with Super-Linearity [8.605514384729469]
  We develop a Super-linear MLIP with both Ultra-Small parameterization and greatly expanded expressive capability, named SUS2-MLIP. SUS2-MLIP outperforms the state-of-the-art MLIP models with its exceptional computational efficiency. This work sheds light on incorporating physical constraints into artificial-intelligence-aided materials simulation.
  arXiv  Detail & Related papers  (2025-02-11T06:34:31Z)
• Teacher-student training improves accuracy and efficiency of machine learning inter-atomic potentials [31.114245664719455]
  Machine learning inter-atomic potentials (MLIPs) are revolutionizing the field of molecular dynamics (MD) simulations. We present a teacher-student training framework in which the latent knowledge from the teacher (atomic energies) is used to augment the students' training. Remarkably, the student models can even surpass the accuracy of the teachers, even though both are trained on the same quantum chemistry dataset.
  arXiv  Detail & Related papers  (2025-02-07T23:20:43Z)
• MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science [62.96434290874878]
  Current Multi-Modal Large Language Models (MLLM) have shown strong capabilities in general visual reasoning tasks. We develop a new framework, named Multi-Modal Scientific Reasoning with Physics Perception and Simulation (MAPS) based on an MLLM. MAPS decomposes expert-level multi-modal reasoning task into physical diagram understanding via a Physical Perception Model (PPM) and reasoning with physical knowledge via a simulator.
  arXiv  Detail & Related papers  (2025-01-18T13:54:00Z)
• CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models [68.64605538559312]
  In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives. Inspired by our findings, we propose a measurement to quantitatively evaluate the learning balance. In addition, we introduce an auxiliary loss regularization method to promote updating of the generation distribution of MLLMs.
  arXiv  Detail & Related papers  (2024-07-29T23:18:55Z)
• Composite Material Design for Optimized Fracture Toughness Using Machine Learning [0.0]
  This paper investigates the optimization of 2D and 3D composite structures using machine learning (ML) techniques. It focuses on fracture toughness and crack propagation in the Double Cantilever Beam (DCB) test.
  arXiv  Detail & Related papers  (2024-06-23T17:01:14Z)
• MLXP: A Framework for Conducting Replicable Experiments in Python [63.37350735954699]
  We propose MLXP, an open-source, simple, and lightweight experiment management tool based on Python. It streamlines the experimental process with minimal overhead while ensuring a high level of practitioner overhead.
  arXiv  Detail & Related papers  (2024-02-21T14:22:20Z)
• Closing the loop: Autonomous experiments enabled by machine-learning-based online data analysis in synchrotron beamline environments [80.49514665620008]
  Machine learning can be used to enhance research involving large or rapidly generated datasets. In this study, we describe the incorporation of ML into a closed-loop workflow for X-ray reflectometry (XRR) We present solutions that provide an elementary data analysis in real time during the experiment without introducing the additional software dependencies in the beamline control software environment.
  arXiv  Detail & Related papers  (2023-06-20T21:21:19Z)
• Theory-Guided Machine Learning for Process Simulation of Advanced Composites [0.0]
  Theory-Guided Machine Learning (TGML) aims to integrate physical laws into ML algorithms. This paper presents three case studies on thermal management during processing of advanced composites.
  arXiv  Detail & Related papers  (2021-03-30T00:49:40Z)
• A Survey on Large-scale Machine Learning [67.6997613600942]
  Machine learning can provide deep insights into data, allowing machines to make high-quality predictions. Most sophisticated machine learning approaches suffer from huge time costs when operating on large-scale data. Large-scale Machine Learning aims to learn patterns from big data with comparable performance efficiently.
  arXiv  Detail & Related papers  (2020-08-10T06:07:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.