Active Learning to Overcome Sample Selection Bias: Application to Photometric Variable Star Classification

TL;DR

This paper demonstrates that active learning effectively mitigates sample selection bias in astronomical classification tasks, significantly improving accuracy and confidence in variable star classification compared to traditional methods.

Contribution

It introduces an active learning framework tailored for astronomical data, showing its superiority over other bias correction methods in variable star classification.

Findings

Active learning reduces classification error rate by over 3%.

Active learning improves agreement with established catalogs from 65.5% to 79.5%.

Classifier confidence increases from 14.6% to 42.9% after active learning.

Abstract

Despite the great promise of machine-learning algorithms to classify and predict astrophysical parameters for the vast numbers of astrophysical sources and transients observed in large-scale surveys, the peculiarities of the training data often manifest as strongly biased predictions on the data of interest. Typically, training sets are derived from historical surveys of brighter, more nearby objects than those from more extensive, deeper surveys (testing data). This sample selection bias can cause catastrophic errors in predictions on the testing data because a) standard assumptions for machine-learned model selection procedures break down and b) dense regions of testing space might be completely devoid of training data. We explore possible remedies to sample selection bias, including importance weighting (IW), co-training (CT), and active learning (AL). We argue that AL---where the data whose inclusion in the training set would most improve predictions on the testing set are queried for manual follow-up---is an effective approach and is appropriate for many astronomical applications. For a variable star classification problem on a well-studied set of stars from Hipparcos and OGLE, AL is the optimal method in terms of error rate on the testing data, beating the off-the-shelf classifier by 3.4% and the other proposed methods by at least 3.0%. To aid with manual labeling of variable stars, we developed a web interface which allows for easy light curve visualization and querying of external databases. Finally, we apply active learning to classify variable stars in the ASAS survey, finding dramatic improvement in our agreement with the ACVS catalog, from 65.5% to 79.5%, and a significant increase in the classifier's average confidence for the testing set, from 14.6% to 42.9%, after a few AL iterations.