Transformer-Based Astronomical Time Series Model with Uncertainty Estimation for Detecting Misclassified Instances

Autor:	Cádiz-Leyton, Martina, Cabrera-Vives, Guillermo, Protopapas, Pavlos, Moreno-Cartagena, Daniel, Donoso-Oliva, Cristobal
Rok vydání:	2024
Předmět:	Astrophysics - Instrumentation and Methods for Astrophysics
Druh dokumentu:	Working Paper
Popis:	In this work, we present a framework for estimating and evaluating uncertainty in deep-attention-based classifiers for light curves for variable stars. We implemented three techniques, Deep Ensembles (DEs), Monte Carlo Dropout (MCD) and Hierarchical Stochastic Attention (HSA) and evaluated models trained on three astronomical surveys. Our results demonstrate that MCD and HSA offers a competitive and computationally less expensive alternative to DE, allowing the training of transformers with the ability to estimate uncertainties for large-scale light curve datasets. We conclude that the quality of the uncertainty estimation is evaluated using the ROC AUC metric. Comment: Accepted for LatinX in AI (LXAI) workshop at the 41 st International Conference on Machine Learning (ICML), Vienna, Austria. PMLR 235, 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2411.01363 Zobrazit plný text záznamu View this record from Arxiv