{
  "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.00150",
  "author_total": 3,
  "authors": [
    {
      "name": "Justin Minggan Wei"
    },
    {
      "name": "Pavlos Protopapas"
    },
    {
      "name": "Guillermo Cabrera-Vives"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/b7y3b08mgsgg9.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.00150",
  "fulltext_url": null,
  "id": "b7y3b08mgsgg9",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.00150",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "astro-ph.IM"
    ],
    [
      "arxiv",
      "cs.CV"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.00150",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/b7y3b08mgsgg9.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:20:59Z",
      "native_id": "2611.00150",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.00150"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.IM",
      "subfield": "instrumentation-methods"
    }
  ],
  "title": "Contrastive Astromer: Two-Stage Contrastive Representation Learning for Astronomical Light Curve Classification",
  "title_text": "Contrastive Astromer: Two-Stage Contrastive Representation Learning for Astronomical Light Curve Classification",
  "type": "preprint",
  "updated_at": "2026-11-05T15:20:18Z",
  "url": "https://research.draconitic.com/paper/b7y3b08mgsgg9",
  "venue": "arXiv",
  "versions": []
}