Active learning with RESSPECT: Resource allocation for extragalactic astronomical transients

TL;DR

This paper evaluates active learning strategies for astronomical transient data, demonstrating their effectiveness in optimizing label acquisition in realistic survey scenarios, and highlights the need for tailored algorithms for such unique data environments.

Contribution

It introduces a realistic simulation framework for testing active learning in astronomy and assesses the robustness of various strategies under complex data conditions.

Findings

Active learning outperforms random sampling in astronomical data labeling.

Complex batch strategies do not significantly outperform simple uncertainty sampling.

Tailored machine learning algorithms are needed for transient detection environments.

Abstract

The recent increase in volume and complexity of available astronomical data has led to a wide use of supervised machine learning techniques. Active learning strategies have been proposed as an alternative to optimize the distribution of scarce labeling resources. However, due to the specific conditions in which labels can be acquired, fundamental assumptions, such as sample representativeness and labeling cost stability cannot be fulfilled. The Recommendation System for Spectroscopic follow-up (RESSPECT) project aims to enable the construction of optimized training samples for the Rubin Observatory Legacy Survey of Space and Time (LSST), taking into account a realistic description of the astronomical data environment. In this work, we test the robustness of active learning techniques in a realistic simulated astronomical data scenario. Our experiment takes into account the evolution of training and pool samples, different costs per object, and two different sources of budget. Results show that traditional active learning strategies significantly outperform random sampling. Nevertheless, more complex batch strategies are not able to significantly overcome simple uncertainty sampling techniques. Our findings illustrate three important points: 1) active learning strategies are a powerful tool to optimize the label-acquisition task in astronomy, 2) for upcoming large surveys like LSST, such techniques allow us to tailor the construction of the training sample for the first day of the survey, and 3) the peculiar data environment related to the detection of astronomical transients is a fertile ground that calls for the development of tailored machine learning algorithms.