HyQ-LC: Improving Light-Curve Classification with Hybrid Quantum--Classical Learning
Abstract
Light curves reveal stellar variability and support studies of stellar evolution and cosmic distances. Reliable classification is therefore important for large time-domain surveys. We present HyQ-LC for ten-class stellar light-curve classification using 359 handcrafted features and 633,034 training objects. The main model combines a window multilayer perceptron (MLP) backbone with a nine-qubit readout using amplitude encoding and angle re-uploading. Both this hybrid and its pure-MLP control have 44,238 parameters. On a shared 20,000-object test set, the hybrid has macro-averaged F1 (Macro-F1) point gains of 0.8276 and 1.2393 percentage points over the pure MLP on two fine-tuning seeds. A separate fixed-fusion configuration achieves slightly higher Macro-F1 but lower accuracy than approximately budget-matched LightGBM. Its positive class-level differences are concentrated in CEP, RRC, and ROT, while the full-budget LightGBM reference scores higher on both metrics. All circuits are simulated classically. The comparisons retain existing validation-selected checkpoints and use the same test objects, with features, predictions, and recomputation code publicly available. The results identify point-estimate improvements over the tested controls while leaving the specific contribution of the quantum branch unresolved.
Related
- Towards Efficient Function Optimisation with Quantum–Classical Hybrid Search
- A Deep Learning Approach to Improving the Arrival-Direction Accuracy of Gamma-Ray Air-Shower Measurements with the Tibet-III Air-Shower Array
- The assembly of bulge-dominated galaxies: two evolutionary channels traced through morphology, kinematics, and environment with a hybrid classification pipeline
- Machine learning-based classification of type 1 active galactic nuclei
- The NEMESIS general young stellar object catalogue. I. Supervised classification with deep learning methods
BibTeX
@misc{yu2026hyqlc,
title = {{HyQ-LC: Improving Light-Curve Classification with Hybrid Quantum--Classical Learning}},
author = {Xinghang Yu and Bin Yang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.26052},
eprint = {2610.26052},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.26052},
}
RIS
TY - UNPB
TI - HyQ-LC: Improving Light-Curve Classification with Hybrid Quantum--Classical Learning
AU - Xinghang Yu
AU - Bin Yang
PY - 2026
DA - 2026/10/19
PB - arXiv
DO - 10.48550/arxiv.2610.26052
UR - https://arxiv.org/abs/2610.26052
AB - Light curves reveal stellar variability and support studies of stellar evolution and cosmic distances. Reliable classification is therefore important for large time-domain surveys. We present HyQ-LC for ten-class stellar light-curve classification using 359 handcrafted features and 633,034 training objects. The main model combines a window multilayer perceptron (MLP) backbone with a nine-qubit readout using amplitude encoding and angle re-uploading. Both this hybrid and its pure-MLP control have 44,238 parameters. On a shared 20,000-object test set, the hybrid has macro-averaged F1 (Macro-F1) point gains of 0.8276 and 1.2393 percentage points over the pure MLP on two fine-tuning seeds. A separate fixed-fusion configuration achieves slightly higher Macro-F1 but lower accuracy than approximately budget-matched LightGBM. Its positive class-level differences are concentrated in CEP, RRC, and ROT, while the full-budget LightGBM reference scores higher on both metrics. All circuits are simulated classically. The comparisons retain existing validation-selected checkpoints and use the same test objects, with features, predictions, and recomputation code publicly available. The results identify point-estimate improvements over the tested controls while leaving the specific contribution of the quantum branch unresolved.
ER -