A General Approach to Domain Adaptation with Applications in Astronomy

Abstract

The ability to build a model on a source task and subsequently adapt such model on a new target task is a pervasive need in many astronomical applications. The problem is generally known as transfer learning in machine learning, where domain adaptation is a popular scenario. An example is to build a predictive model on spectroscopic data to identify Supernovae IA, while subsequently trying to adapt such model on photometric data. In this paper we propose a new general approach to domain adaptation that does not rely on the proximity of source and target distributions. Instead we simply assume a strong similarity in model complexity across domains, and use active learning to mitigate the dependency on source examples. Our work leads to a new formulation for the likelihood as a function of empirical error using a theoretical learning bound; the result is a novel mapping from generalization error to a likelihood estimation. Results using two real astronomical problems, Supernova Ia classification and identification of Mars landforms, show two main advantages with our approach: increased accuracy performance and substantial savings in computational cost.

DeepShadows: Separating Low Surface Brightness Galaxies from Artifacts using Deep Learning

“…Here our exploration was minimal, either applying the model trained on DES data directly to HSC SSP data or retraining the whole model on a very small set from HSC SSP. More domain adaptation techniques (e.g., Kouw and Loog, 2018;Wang and Deng, 2018) (techniques that use algorithms trained in one or more "source domains" to a different, but related, "target domain") should be explored before choosing an approach to apply to forthcoming surveys (for domain adaptation applications in astronomy, see e.g., Vilalta et al 2019;Ćiprijanović et al 2020a). These techniques would allow the models to be successfully applied to the new data without the need to retrain the model later and more importantly to manually label new "target" datasets since these techniques often use unlabeled target datasets.…”

Locating Hidden Exoplanets in ALMA Data Using Machine Learning

“…Any differences in performance of the models between the codes, e.g., if the models consistently performed better on SPH data, would be difficult to interpret, and the cause could be hard to identify. It is possible that the method of domain adaptation (Ben-David et al 2010), which has already found success in astronomy (Vilalta et al 2019;Alexander et al 2021;Ćiprijanović et al 2022), could be used to encourage the models to overcome any differences between data sets. This is an avenue that is ripe for exploration in future work.…”

Active deep learning method for the discovery of objects of interest in large spectroscopic surveys

“…Active learning has already shown to be successful in astronomy, for example, in estimating parameters of stellar population synthesis models by Solorio et al (2005) or for the classification of light curves of variable stars by Richards et al (2012). Gupta et al (2016) used active learning to learn a model for photometric data classification from spectroscopic data (the work was extended by Vilalta et al (2019)), and recently, active learning was used to minimise the number of required spectroscopically confirmed labels in preparing training sets for the photometric classification of supernova light curves by Ishida et al (2019a) and for active anomaly detection in light curves of supernovae by Ishida et al (2019b). Moreover, active deep learning has been successfully tested in remote sensing by Liu et al (2017), with further examples reviewed in Yang et al (2018).…”