Multiband astronomical time series exhibit heterogeneous variability patterns, sampling cadences, and signal characteristics across bands. Standard transformers apply shared parameters to all bands, potentially limiting their ability to model this rich structure. In this work, we introduce Astro-MoE, a foundational transformer architecture that enables dynamic processing via a Mixture of Experts module. We validate our model on both simulated (ELAsTiCC-1) and real-world datasets (Pan-STARRS1).
@article{arxiv.2507.12611,
title = {Astro-MoE: Mixture of Experts for Multiband Astronomical Time Series},
author = {Martina Cádiz-Leyton and Guillermo Cabrera-Vives and Pavlos Protopapas and Daniel Moreno-Cartagena and Ignacio Becker},
journal= {arXiv preprint arXiv:2507.12611},
year = {2025}
}
Comments
Accepted at the 2025 Workshop on Machine Learning for Astrophysics