Is Self-Supervised Pretraining Good for Extrapolation in Molecular Property Prediction?

TL;DR

This paper investigates whether self-supervised pretraining can improve the ability of machine learning models to extrapolate unobserved material properties, showing it helps models learn relative tendencies despite not predicting exact values.

Contribution

The study provides an experimental framework demonstrating that self-supervised pretraining enhances relative extrapolation in material property prediction tasks.

Findings

Self-supervised pretraining improves models' ability to learn relative property tendencies.

Models still struggle with accurate absolute property extrapolation.

Pretraining enables better generalization beyond observed data.

Abstract

The prediction of material properties plays a crucial role in the development and discovery of materials in diverse applications, such as batteries, semiconductors, catalysts, and pharmaceuticals. Recently, there has been a growing interest in employing data-driven approaches by using machine learning technologies, in combination with conventional theoretical calculations. In material science, the prediction of unobserved values, commonly referred to as extrapolation, is particularly critical for property prediction as it enables researchers to gain insight into materials beyond the limits of available data. However, even with the recent advancements in powerful machine learning models, accurate extrapolation is still widely recognized as a significantly challenging problem. On the other hand, self-supervised pretraining is a machine learning technique where a model is first trained on unlabeled data using relatively simple pretext tasks before being trained on labeled data for target tasks. As self-supervised pretraining can effectively utilize material data without observed property values, it has the potential to improve the model's extrapolation ability. In this paper, we clarify how such self-supervised pretraining can enhance extrapolation performance.We propose an experimental framework for the demonstration and empirically reveal that while models were unable to accurately extrapolate absolute property values, self-supervised pretraining enables them to learn relative tendencies of unobserved property values and improve extrapolation performance.