Fine-Tuning Unifies Foundational Machine-learned Interatomic Potential Architectures at ab initio Accuracy
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911253951152128 |
|---|---|
| author | Hänseroth, Jonas Flötotto, Aaron Qaisrani, Muhammad Nawaz Dreßler, Christian |
| author_facet | Hänseroth, Jonas Flötotto, Aaron Qaisrani, Muhammad Nawaz Dreßler, Christian |
| contents | This work demonstrates that fine-tuning transforms foundational machine-learned interatomic potentials (MLIPs) to achieve consistent, near-ab initio accuracy across diverse architectures. Benchmarking five leading MLIP frameworks (MACE, GRACE, SevenNet, MatterSim, and ORB) across seven chemically diverse compounds reveals that fine-tuning universally enhances force predictions by factors of 5-15 and improves energy accuracy by 2-4 orders of magnitude. The investigated models span both equivariant and invariant, as well as conservative and non-conservative, architectures. While general-purpose foundation models are robust, they exhibit architecture-dependent deviations from ab initio reference data; fine-tuning eliminates these discrepancies, enabling quantitatively accurate predictions of atomistic and structural properties. Using datasets constructed from equidistantly sampled frames of short ab initio molecular dynamics trajectories, fine-tuning reduces force errors by an order of magnitude and harmonizes performance across all architectures. These findings establish fine-tuning as a universal route to achieving system-specific predictive accuracy while preserving the computational efficiency of MLIPs. To promote widespread adoption, we introduce the aMACEing Toolkit, which provides a unified and reproducible interface for fine-tuning workflows across multiple MLIP frameworks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05337 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-Tuning Unifies Foundational Machine-learned Interatomic Potential Architectures at ab initio Accuracy Hänseroth, Jonas Flötotto, Aaron Qaisrani, Muhammad Nawaz Dreßler, Christian Chemical Physics Computational Physics This work demonstrates that fine-tuning transforms foundational machine-learned interatomic potentials (MLIPs) to achieve consistent, near-ab initio accuracy across diverse architectures. Benchmarking five leading MLIP frameworks (MACE, GRACE, SevenNet, MatterSim, and ORB) across seven chemically diverse compounds reveals that fine-tuning universally enhances force predictions by factors of 5-15 and improves energy accuracy by 2-4 orders of magnitude. The investigated models span both equivariant and invariant, as well as conservative and non-conservative, architectures. While general-purpose foundation models are robust, they exhibit architecture-dependent deviations from ab initio reference data; fine-tuning eliminates these discrepancies, enabling quantitatively accurate predictions of atomistic and structural properties. Using datasets constructed from equidistantly sampled frames of short ab initio molecular dynamics trajectories, fine-tuning reduces force errors by an order of magnitude and harmonizes performance across all architectures. These findings establish fine-tuning as a universal route to achieving system-specific predictive accuracy while preserving the computational efficiency of MLIPs. To promote widespread adoption, we introduce the aMACEing Toolkit, which provides a unified and reproducible interface for fine-tuning workflows across multiple MLIP frameworks. |
| title | Fine-Tuning Unifies Foundational Machine-learned Interatomic Potential Architectures at ab initio Accuracy |
| topic | Chemical Physics Computational Physics |
| url | https://arxiv.org/abs/2511.05337 |