Deep Transfer Learning for Classification of Variable Sources

Abstract

Ongoing or upcoming surveys such as Gaia, ZTF, or LSST will observe light-curves of billons or more astronomical sources. This presents new challenges for identifying interesting and important types of variability. Collecting a sufficient number of labelled data for training is difficult, however, especially in the early stages of a new survey. Here we develop a single-band light-curve classifier based on deep neural networks, and use transfer learning to address the training data paucity problem by conveying knowledge from one dataset to another. First we train a neural network on 16 variability features extracted from the light-curves of OGLE and EROS-2 variables. We then optimize this model using a small set (e.g. 5%) of periodic variable light-curves from the ASAS dataset in order to transfer knowledge inferred from OGLE/EROS-2 to a new ASAS classifier. With this we achieve good classification results on ASAS, thereby showing that knowledge can be successfully transferred between datasets. We demonstrate similar transfer learning using Hipparcos and ASAS-SN data. We therefore find that it is not necessary to train a neural network from scratch for every new survey, but rather that transfer learning can be used even when only a small set of labelled data is available in the new survey.

arXiv comment18 pages, 12 figures, 8 tables, Accepted for publication in Astronomy & Astrophysics

References in corpus (41)

• Adam: A Method for Stochastic Optimization
• SMOTE: Synthetic Minority Over-sampling Technique
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Distilling the Knowledge in a Neural Network
• The Gaia mission
• ADADELTA: An Adaptive Learning Rate Method
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• The Man Behind the Curtain: X-rays Drive the UV through NIR Variability in the 2013 AGN Outburst in NGC 2617
• Limits on the Macho Content of the Galactic Halo from the EROS-2 Survey of the Magellanic Clouds
• The Pan-STARRS1 Surveys
• SkyMapper and the Southern Sky Survey
• The ASAS-SN Catalog of Variable Stars I: The Serendipitous Survey
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Random forest automated supervised classification of Hipparcos periodic variable stars
• The ASAS-SN Catalog of Variable Stars III: Variables in the Southern TESS Continuous Viewing Zone
• Photometric redshift estimation via deep learning
• Using transfer learning to detect galaxy mergers
• TACT: A Transfer Actor-Critic Learning Framework for Energy Saving in Cellular Radio Access Networks
• Searching for Exoplanets Using Artificial Intelligence
• QSO Selection Algorithm Using Time Variability and Machine Learning: Selection of 1,620 QSO Candidates from MACHO LMC Database
• Transfer learning for galaxy morphology from one survey to another
• The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database
• A Package for the Automated Classification of Periodic Variable Stars
• Deep Learning Classification in Asteroseismology
• Quasar and galaxy classification in Gaia Data Release 2
• DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning
• DeepSource: Point Source Detection using Deep Learning
• A machine learned classifier for RR Lyrae in the VVV survey
• Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
• Detecting solar system objects with convolutional neural networks
• Transfer learning for radio galaxy classification
• Comparing Multi-class, Binary and Hierarchical Machine Learning Classification schemes for variable stars
• A Refined QSO Selection Method Using Diagnostics Tests: 663 QSO Candidates in the LMC
• Measurement of quark- and gluon-like jet fractions using jet charge in PbPb and pp collisions at 5.02 TeV
• Higgs self-coupling measurements using deep learning in the $b\bar{b}b\bar{b}$ final state
• Uncertainty Quantification for Data-driven Turbulence Modelling with Mondrian Forests
• Optimizing Automated Classification of Periodic Variable Stars in New Synoptic Surveys
• Speech Recognition with Deep Recurrent Neural Networks
• Transfer Meets Hybrid: A Synthetic Approach for Cross-Domain Collaborative Filtering with Text
• New variable stars in the Galactic Bulge: I. The bright regime

Cited by in corpus (3)

• The automation of optical transient discovery and classification in Rubin-era time-domain astronomy
• A New Period Determination Method for Periodic Variable Stars
• Convolutional Deep Denoising Autoencoders for Radio Astronomical Images