通过校准不确定性生成对抗结构，精准控制模型预测误差。
Learning atomic forces from uncertainty-calibrated adversarial attacks
- 用校准后的不确定性指导对抗结构优化
- 仅需数百样本即收敛水与金属有机框架的物性
- 适合需要高可靠性势函数的研究者
对抗方法通过生成困难样本提升机器学习原子间势（MLIPs）性能。然而，目前对MLIP在对抗结构上的实际预测误差及其可控性仍缺乏了解。本文提出校准对抗几何优化（CAGO）算法，可生成具有用户指定误差的对抗结构。通过不确定性校准，将模型估计的不确定性与真实误差统一。基于校准后的不确定性进行几何优化，实现目标预测误差的对抗结构生成。结合主动学习流程，验证了CAGO在仅数百个训练结构下，即可系统收敛液态水及金属有机框架中水吸附的结构、动力学和热力学性质，显著优于以往需数千样本的方法。
原文摘要 · Abstract (English)
Adversarial approaches, which intentionally challenge machine learning models by generating difficult examples, are increasingly being adopted to improve machine learning interatomic potentials (MLIPs). While already providing great practical value, little is known about the actual prediction errors of MLIPs on adversarial structures and whether these errors can be controlled. We propose the Calibrated Adversarial Geometry Optimization (CAGO) algorithm to discover adversarial structures with user-assigned errors. Through uncertainty calibration, the estimated uncertainty of MLIPs is unified with real errors. By performing geometry optimization for calibrated uncertainty, we reach adversarial structures with the user-assigned target MLIP prediction error. Integrating with active learning pipelines, we benchmark CAGO, demonstrating stable MLIPs that systematically converge structural, dynamical, and thermodynamical properties for liquid water and water adsorption in a metal-organic framework within only hundreds of training structures, where previously many thousands were typically required.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。