在属性指定的化学特征空间中采用最远点采样作为提升小规模化学数据集机器学习模型性能的一般策略
Farthest Point Sampling in Property Designated Chemical Feature Space as a General Strategy for Enhancing the Machine Learning Model Performance for Small Scale Chemical Dataset
AI总结：
本文研究了在目标化学特征空间中使用最远点采样策略生成均衡训练数据集，从而提升机器学习模型性能，证明了该策略在小规模且不平衡数据集中的有效性。
摘要：
在化学和材料科学中，机器学习模型开发常常面临小规模、不平衡标记数据集的挑战，这是科学实验中的常见限制。这些数据不平衡可能导致过拟合并降低模型的泛化能力。本研究探讨了在目标化学特征空间中使用最远点采样（FPS）策略的有效性，展示了其生成良好分布的训练数据集的能力，从而提高模型性能。我们通过包括人工神经网络（ANN）、支持向量机（SVM）和随机森林（RF）在内的各种机器学习模型，使用包含物理化学性质如标准沸点和蒸发热的数据集，严格评估了该策略。我们的发现表明，基于FPS的模型在小规模训练数据集上表现尤为突出，具有更高的预测精度和鲁棒性，同时显著减少了过拟合。这种改进归因于训练数据化学特征空间内的增加多样性。因此，FPS成为了一种普遍有效且适应性强的方法，用于通过小规模和偏倚的实验数据集来实现高性能的机器学习模型。
英文摘要：
Machine learning model development in chemistry and materials science often grapples with the challenge of small scale, unbalanced labelled datasets, a common limitation in scientific experiments. These dataset imbalances can precipitate overfit ting and diminish model generalization. Our study explores the efficacy of the farthest point sampling (FPS) strategy within target ed chemical feature spaces, demonstrating its capacity to generate well-distributed training datasets and consequently enhance model performance. We rigorously evaluated this strategy across various machine learning models, including artificial neural net works (ANN), support vector machines (SVM), and random forests (RF), using datasets encapsulating physicochemical properties like standard boiling points and enthalpy of vaporization. Our findings reveal that FPS-based models consistently surpass those trained via random sampling, exhibiting superior predictive accuracy and robustness, alongside a marked reduction in overfitting. This improvement is particularly pronounced in smaller training datasets, attributable to increased diversity within the training data's chemical feature space. Consequently, FPS emerges as a universally effective and adaptable approach in approaching high performance machine learning models by small and biased experimental datasets prevalent in chemistry and materials science.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
