A General Approach to Domain Adaptation with Applications in Astronomy
Abstract
The ability to build a model on a source task and subsequently adapt this model to a new target task is a pervasive need in many astronomical applications. The problem is generally known in the machine learning field as transfer learning, where domain adaptation is a popular scenario. An example is to build a predictive model on spectroscopic data to identify Type Ia supernovae (SNe Ia), while subsequently trying to adapt such a model to photometric data. In this paper we propose a new general approach to domain adaptation which 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 dependence 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, SN Ia classification and identification of Mars landforms, show two main advantages of our approach: increased performance accuracy and substantial savings in computational cost.
- Publication:
-
Publications of the Astronomical Society of the Pacific
- Pub Date:
- October 2019
- DOI:
- 10.1088/1538-3873/aaf1fc
- arXiv:
- arXiv:1812.08839
- Bibcode:
- 2019PASP..131j8008V
- Keywords:
-
- Computer Science - Machine Learning;
- Statistics - Machine Learning
- E-Print:
- doi:10.1088/1538-3873/aaf1fc