A brief review of contrastive learning applied to astrophysics

TL;DR

This paper reviews how contrastive learning, a self-supervised machine learning approach, is applied to astronomy for pattern extraction, instrumental effect removal, and classification with limited labels, highlighting promising applications and practical tips.

Contribution

It provides a concise overview of contrastive learning concepts and reviews its initial successful applications in astrophysics, emphasizing its potential for foundation models.

Findings

Contrastive learning effectively removes instrumental effects in astronomical data.

It enables classification and regression with limited labeled data.

Promising applications include foundation models in astronomy.

Abstract

Reliable tools to extract patterns from high-dimensionality spaces are becoming more necessary as astronomical datasets increase both in volume and complexity. Contrastive Learning is a self-supervised machine learning algorithm that extracts informative measurements from multi-dimensional datasets, which has become increasingly popular in the computer vision and Machine Learning communities in recent years. To do so, it maximizes the agreement between the information extracted from augmented versions of the same input data, making the final representation invariant to the applied transformations. Contrastive Learning is particularly useful in astronomy for removing known instrumental effects and for performing supervised classifications and regressions with a limited amount of available labels, showing a promising avenue towards \emph{Foundation Models}. This short review paper briefly summarizes the main concepts behind contrastive learning and reviews the first promising applications to astronomy. We include some practical recommendations on which applications are particularly attractive for contrastive learning.