StarCLR: Contrastive Learning Representation for Astronomical Light Curves
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917440071401472 |
|---|---|
| author | Ding, Junyao Chen, Xiaodian Gao, Xinyi Tang, Xiaoyu Wang, Shu Huang, Yang Qi, Xinyu Xue, Guirong Luo, Ali Liu, Jifeng |
| author_facet | Ding, Junyao Chen, Xiaodian Gao, Xinyi Tang, Xiaoyu Wang, Shu Huang, Yang Qi, Xinyu Xue, Guirong Luo, Ali Liu, Jifeng |
| contents | With the rapid development of time-domain surveys, the availability of massive light curve data offers new opportunities for studying stellar evolution and variable star classification, while simultaneously posing challenges for feature extraction and modeling. We present StarCLR, a contrastive pretraining framework for large-scale light curves. By constructing positive pairs from partially overlapping sub-sequences, StarCLR encourages the model to learn temporal representations. We pretrain StarCLR on the TESS dataset and fine-tune it for variable star classification on three surveys with distinct observational characteristics, namely TESS (18 types), ZTF (11 types), and Gaia (24 types). StarCLR achieves macro-F1 scores of 84.35%, 87.82%, and 92.73%, and micro-F1 scores of 94.46%, 92.83%, and 99.49%, respectively. Compared with LSTM and Transformer trained from scratch, StarCLR performs better on TESS and ZTF, with the largest gains on sparsely sampled ZTF light curves, demonstrating promising generalization. For Gaia, which involves a broader class space, the evaluation is not directly comparable, and performance is likely influenced by astrophysical features, resulting in a more limited contribution from the pretrained backbone. Systematic ablations on embedding design, pooling strategy, and pretraining settings further indicate that the pretrained representations provide performance gains by capturing informative temporal characteristics of light curves. Looking ahead, with standardized datasets and more diverse labeling schemes, the generalization ability of StarCLR can be further enhanced. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_24516 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | StarCLR: Contrastive Learning Representation for Astronomical Light Curves Ding, Junyao Chen, Xiaodian Gao, Xinyi Tang, Xiaoyu Wang, Shu Huang, Yang Qi, Xinyu Xue, Guirong Luo, Ali Liu, Jifeng Solar and Stellar Astrophysics Instrumentation and Methods for Astrophysics With the rapid development of time-domain surveys, the availability of massive light curve data offers new opportunities for studying stellar evolution and variable star classification, while simultaneously posing challenges for feature extraction and modeling. We present StarCLR, a contrastive pretraining framework for large-scale light curves. By constructing positive pairs from partially overlapping sub-sequences, StarCLR encourages the model to learn temporal representations. We pretrain StarCLR on the TESS dataset and fine-tune it for variable star classification on three surveys with distinct observational characteristics, namely TESS (18 types), ZTF (11 types), and Gaia (24 types). StarCLR achieves macro-F1 scores of 84.35%, 87.82%, and 92.73%, and micro-F1 scores of 94.46%, 92.83%, and 99.49%, respectively. Compared with LSTM and Transformer trained from scratch, StarCLR performs better on TESS and ZTF, with the largest gains on sparsely sampled ZTF light curves, demonstrating promising generalization. For Gaia, which involves a broader class space, the evaluation is not directly comparable, and performance is likely influenced by astrophysical features, resulting in a more limited contribution from the pretrained backbone. Systematic ablations on embedding design, pooling strategy, and pretraining settings further indicate that the pretrained representations provide performance gains by capturing informative temporal characteristics of light curves. Looking ahead, with standardized datasets and more diverse labeling schemes, the generalization ability of StarCLR can be further enhanced. |
| title | StarCLR: Contrastive Learning Representation for Astronomical Light Curves |
| topic | Solar and Stellar Astrophysics Instrumentation and Methods for Astrophysics |
| url | https://arxiv.org/abs/2604.24516 |