.png){kind=icon}
返回
Extrapolation validation (EV): a universal validation method for mitigating machine learning extrapolation risk
.png){kind=icon}
OA
AI
DOI：10.1039/d3dd00256j.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Machine learning (ML) can provide decision-making advice for major challenges in science and engineering, and its rapid development has led to advances in fields like chemistry & medicine, earth & life sciences, and communications & transportation. Grasping the trustworthiness of the decision-making advice given by ML models remains challenging, especially when applying them to samples outside the domain-of-application. Here, an untrustworthy application situation (i.e., complete extrapolation-failure) that would occur in models developed by ML methods involving tree algorithms is confirmed, and the root cause of its difficulty in discovering novel materials & chemicals is revealed. Furthermore, a universal extrapolation risk evaluation scheme, termed the extrapolation validation (EV) method, is proposed, which is not restricted to specific ML methods and model architecture in its applicability. The EV method quantitatively evaluates the extrapolation ability of 11 popularly applied ML methods and digitalizes the extrapolation risk arising from variations of the independent variables in each method. Meanwhile, the EV method provides insights and solutions for evaluating the reliability of out-of-distribution sample prediction and selecting trustworthy ML methods. A generic machine learning model validation method named extrapolation validation (EV) has been proposed, which evaluates the trustworthiness of model predictions to mitigate the extrapolation risk before the model transitions to applications.
Keyword:
PREDICTION
期刊
IF:
5.6
论文数:
1.0K
被引数:
1.9K
机构
引用论文
Emerging materials intelligence ecosystems propelled by machine learning机器学习推动的新兴材料智能生态系统.png)
NATURE REVIEWS MATERIALS
NATURE REVIEWS MATERIALSIF86.2
PREAI
分享收藏Retrosynthesis prediction with an interpretable deep-learning framework based on molecular assembly tasks基于分子组装任务的可解释深度学习框架的逆向合成预测NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Maximum Efficient Power Performance Analysis and Multi-Objective Optimization of Two-Stage Thermoelectric GeneratorsEntropyOAAI
EntropyIF0
OAAI分享收藏分享收藏
查看更多内容