Contrastive Astromer: Two-Stage Contrastive Representation Learning for Astronomical Light Curve Classification
astro-ph.IM, cs.CV
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/astromer-science/main-code
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large astronomical surveys collect abundant light curves, but reliable class labels remain scarce.
Terminology
Abstract
Large astronomical surveys collect abundant light curves, but reliable class labels remain scarce. ASTROMER 2 learns from unlabeled light curves by reconstructing masked observations, yet this objective does not explicitly encourage class separation in a compact representation of each light curve. We introduce Contrastive Astromer, a two-stage approach that makes these representations more useful for classification without changing the ASTROMER 2 encoder architecture. First, unsupervised contrastive learning on single-band MACHO light curves brings together representations of augmented views of the same object. Supervised contrastive learning, supported by an auxiliary classification loss, then uses a separate labeled Alcock sample to strengthen class discrimination. We evaluate the resulting representations by freezing the encoder and training a separate classifier. On a held-out set of 600 objects, this classifier achieves a macro-F1 of 0.7943 with 500 labeled examples per class, exceeding our reproduction of the ASTROMER 2 finetune-and-classify pipeline by 5.10 percentage points. With downstream classifier training budgets of 20 and 100 examples per class, macro-F1 reaches 0.7078 and 0.7704, respectively, also surpassing this baseline. Embedding-space analyses further show that supervised adaptation improves local class consistency and global class separation. These results show that contrastive adaptation makes pretrained light-curve representations more effective for classification and more informative about the structure of variability classes.
Sources
- The Zwicky Transient Facility: System Overview, Performance, and First Results
- On the Opportunities and Risks of Foundation Models
- Astro-MoE: Mixture of Experts for Multiband Astronomical Time Series
- StarCLR: Contrastive Learning Representation for Astronomical Light Curves
- Astromer 2
- ASTROMER: A transformer-based embedding for the representation of light curves
- Variable stars across the observational HR diagram
- Supervised Contrastive Learning
- AstroCLIP: A Cross-Modal Foundation Model for Galaxies
- Representation Learning with Contrastive Predictive Coding
- AstroM$^3$: A self-supervised multimodal model for astronomy
- ATLAS: A High-Cadence All-Sky Survey System
- Maven: A Multimodal Foundation Model for Supernova Science
Related papers
- On-sky demonstration of a vector Zernike wavefront sensor in a cascaded adaptive optics system
- Euclid Data Release 1 (DR1): Calibration strategy and observations
- The General Antiparticle Spectrometer (GAPS) Antarctic Balloon Payload
- Detection and excision of radio-frequency interference in radio arrays
- Unified matched-filter and excess-power pipeline for gravitational-wave detector characterization
- Ushering in sub-arcsecond angular resolution observatories in the far-infrared: The case for a double-Fourier interferometer