This website requires JavaScript.

ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction

Dawid RymarczykDaniel DobrowolskiTomasz Danel
Oct 2022
摘要
In this work, we propose the novel Prototypical Graph RegressionSelf-explainable Trees (ProGReST) model, which combines prototype learning,soft decision trees, and Graph Neural Networks. In contrast to other works, ourmodel can be used to address various challenging tasks, including compoundproperty prediction. In ProGReST, the rationale is obtained along withprediction due to the model's built-in interpretability. Additionally, weintroduce a new graph prototype projection to accelerate model training.Finally, we evaluate PRoGReST on a wide range of chemical datasets formolecular property prediction and perform in-depth analysis with chemicalexperts to evaluate obtained interpretations. Our method achieves competitiveresults against state-of-the-art methods.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答