ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction

TL;DR

ProGReST is an interpretable graph neural network model that combines prototype learning and soft decision trees to predict molecular properties, providing explanations and achieving competitive accuracy.

Contribution

It introduces a novel ProGReST model integrating prototypes, soft trees, and GNNs for explainable molecular property prediction, with a new graph prototype projection for faster training.

Findings

Achieves competitive results on chemical datasets.

Provides built-in interpretability with chemical expert validation.

Introduces a graph prototype projection method for training acceleration.

Abstract

In this work, we propose the novel Prototypical Graph Regression Self-explainable Trees (ProGReST) model, which combines prototype learning, soft decision trees, and Graph Neural Networks. In contrast to other works, our model can be used to address various challenging tasks, including compound property prediction. In ProGReST, the rationale is obtained along with prediction due to the model's built-in interpretability. Additionally, we introduce a new graph prototype projection to accelerate model training. Finally, we evaluate PRoGReST on a wide range of chemical datasets for molecular property prediction and perform in-depth analysis with chemical experts to evaluate obtained interpretations. Our method achieves competitive results against state-of-the-art methods.