English

ASTROCO: Self-Supervised Conformer-Style Transformers for Light-Curve Embeddings

Instrumentation and Methods for Astrophysics 2025-09-30 v1 Artificial Intelligence Machine Learning

Abstract

We present AstroCo, a Conformer-style encoder for irregular stellar light curves. By combining attention with depthwise convolutions and gating, AstroCo captures both global dependencies and local features. On MACHO R-band, AstroCo outperforms Astromer v1 and v2, yielding 70 percent and 61 percent lower error respectively and a relative macro-F1 gain of about 7 percent, while producing embeddings that transfer effectively to few-shot classification. These results highlight AstroCo's potential as a strong and label-efficient foundation for time-domain astronomy.

Cite

@article{arxiv.2509.24134,
  title  = {ASTROCO: Self-Supervised Conformer-Style Transformers for Light-Curve Embeddings},
  author = {Antony Tan and Pavlos Protopapas and Martina Cádiz-Leyton and Guillermo Cabrera-Vives and Cristobal Donoso-Oliva and Ignacio Becker},
  journal= {arXiv preprint arXiv:2509.24134},
  year   = {2025}
}

Comments

Accepted at the NeurIPS 2025 Workshop on Machine Learning and the Physical Sciences (ML4PS), camera-ready version in progress

R2 v1 2026-07-01T06:03:11.699Z