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