Scholarlink

<p>Accurately predicting polymer density from SMILES strings remains challenging due to the small size, high noise, and chemically diversity of typical datasets. We introduce LiteBoost, a deliberately minimalist gradient boosting model that employs shallow, three-level symmetric trees and exposes only two tunable hyperparameters (<i>n_estimators</i> and <i>learning_rate</i>). Using a curated dataset of 613 polymers, we benchmark LiteBoost against ExtraTrees, XGBoost, LightGBM, and CatBoost, optimizing each with 100–1000 Optuna trials and evaluating performance across seven complementary metrics: R<sup>2</sup>, RMSE, MAE, median AE, MAPE, maximum error, and explained variance. LiteBoost achieves a MAE of 0.031&#xa0;g/cm<sup>3</sup>, RMSE of 0.062&#xa0;g/cm<sup>3</sup>, R<sup>2</sup> of 0.81, and MAPE of 3.03%, all within 2–3% of the best-in-class CatBoost and XGBoost scores and well within the bounds of experimental uncertainty. Crucially, it does so with orders-of-magnitude fewer hyperparameters. These results demonstrates that a streamlined boosting model can rival heavyweight ensembles in accuracy while dramatically reducing tuning effort, computational cost, and interpretability barriers. LiteBoost is thus a practical first-line surrogate model for high-throughput polymer screening and inverse-design workflows where speed, robustness, and transparency are as critical as raw predictive power.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

LiteBoost: a lightweight and explainable boosting model for predicting polymer density from SMILES data

  • 期刊论文

  • 发表日期：

    2025年11月14日

查看全文
  • Tuan Nguyen-Sy,
  • Hieu Do-Trung,
  • Nam Nguyen-Hoang,
  • Duc Toan Truong,
  • My-Kristyna Nguyen-Thao

摘要

Accurately predicting polymer density from SMILES strings remains challenging due to the small size, high noise, and chemically diversity of typical datasets. We introduce LiteBoost, a deliberately minimalist gradient boosting model that employs shallow, three-level symmetric trees and exposes only two tunable hyperparameters (n_estimators and learning_rate). Using a curated dataset of 613 polymers, we benchmark LiteBoost against ExtraTrees, XGBoost, LightGBM, and CatBoost, optimizing each with 100–1000 Optuna trials and evaluating performance across seven complementary metrics: R2, RMSE, MAE, median AE, MAPE, maximum error, and explained variance. LiteBoost achieves a MAE of 0.031 g/cm3, RMSE of 0.062 g/cm3, R2 of 0.81, and MAPE of 3.03%, all within 2–3% of the best-in-class CatBoost and XGBoost scores and well within the bounds of experimental uncertainty. Crucially, it does so with orders-of-magnitude fewer hyperparameters. These results demonstrates that a streamlined boosting model can rival heavyweight ensembles in accuracy while dramatically reducing tuning effort, computational cost, and interpretability barriers. LiteBoost is thus a practical first-line surrogate model for high-throughput polymer screening and inverse-design workflows where speed, robustness, and transparency are as critical as raw predictive power.