Active Learning for Stellar Spectral Classification

Supervised machine learning models are increasingly being used for solving the problem of stellar classification of spectroscopic data. However, training such models requires a large number of labelled instances, the collection of which is usually costly in both time and expertise. This paper explores the application of active learning algorithms to sampling stellar spectra using data from a highly class-imbalanced dataset. We utilize the MaStar library from the SDSS DR17 along with its associated stellar parameter catalogue. Using different active learning algorithms, we iteratively select informative instances, where the model or committee of models exhibits the highest uncertainty or disagreement, respectively. We assess the effectiveness of the sampling techniques by comparing several performance metrics of supervised-learning models trained on the queried samples with randomly-sampled counterparts. Evaluation metrics include specificity, sensitivity, and the area under the curve, in addition to the Matthew\'s correlation coefficient, which offers a more-balanced assessment that considers all aspects of the confusion matrix, and is thus more suitable for use with imbalanced datasets. We apply this procedure to effective temperature, surface gravity, and iron metallicity, separately. Our results demonstrate the effectiveness of active learning algorithms in selecting samples that produce performance metrics superior to random sampling and even stratified samples. We discuss the implications of the findings for prioritizing instance labelling of astronomical-survey data by experts or crowdsourcing to mitigate the high time cost.