TabPFN 用于含能材料性质预测，超越 XGBoost 与 Chemprop

实验对比覆盖多种主流方法，包括调优后的 XGBoost 梯度提升、随机森林和高斯过程，TabPFN 都显著胜出。即便输入 Chemprop 消息传递神经网络学到的分子表示，TabPFN 依然比 Chemprop 自身的预测更准确，说明其优势不依赖手工特征。速度方面，TabPFN 比 XGBoost 快一个数量级以上，并且它预测目标的整个分布而非单一数值，自带不确定性量化，作者还用重复测量的经验分布验证了这一点。

论文最后用 Shapley 值对预测做解释，按重要性排列特征。对从事材料性质建模的研究者来说，这篇工作的意义在于：一个免调参的预训练表格模型可以直接替换传统的特征工程加调参流程，在化学小数据集上同样成立。

Accurate predictions of properties of energetic materials with tabular foundation models

We use TabPFN, a recently developed tabular foundation model, to predict three properties of energetic materials: impact sensitivity, decomposition temperature and crystal density. Without any hyperparameter tuning, TabPFN outperforms the best published models for all three properties. It also substantially outperforms a wide range of established machine-learning models, including tuned gradient boosting (XGBoost), random forests and Gaussian processes. This holds both when the models are given hand-crafted molecular descriptors and when they are given learned representations from Chemprop's message-passing neural network. In particular, for all three properties, TabPFN applied to Chemprop's own embedding is more accurate than Chemprop's predictions. TabPFN is also among the fastest models we consider, more than an order of magnitude faster than XGBoost. As TabPFN predicts the entire distribution of the target rather than just a single value, it offers built-in uncertainty quantification, which we compare with the empirical distributions of compounds with repeated measurements. Finally, we interpret the predictions using Shapley values, which rank the features by their importance.

This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include TabPFN, XGBoost, Chemprop, 表格基础模型.

Source attribution: curated from arXiv cs.LG (@Vagn Krister Nes Glomsrud, Mathias Bynke, Lars Henry Berge Olsen, Dennis Christensen).