2023/12/04 by V. Ashley Villar, Villar, V. Ashley, Kaylee de Soto +3 · 1 citation
Medicine · #FOS: Physical sciences #Heart Rate Variability and Autonomic Control #High Energy Astrophysical Phenomena (astro-ph.HE) #Hormonal and reproductive studies #Instrumentation and Methods for Astrophysics (astro-ph.IM)
paper · pdf · doi:10.48550/arxiv.2312.02266
openalex publication_date 2023/12/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Astrophysical transient phenomena are traditionally classified spectroscopically in a hierarchical taxonomy; however, this graph structure is currently not utilized in neural net-based photometric classifiers for time-domain astrophysics. Instead, independent classifiers are trained for different tiers of classified data, and events are excluded if they fall outside of these well-defined but flat classification schemes. Here, we introduce a weighted hierarchical cross-entropy objective function for classification of astrophysical transients. Our method allows users to directly build and use physics- or observationally-motivated tree-based taxonomies. Our weighted hierarchical cross-entropy loss directly uses this graph to accurately classify all targets into any node of the tree, re-weighting imbalanced classes. We test our novel loss on a set of variable stars and extragalactic transients from the Zwicky Transient Facility, showing that we can achieve similar performance to fine-tuned classifiers with the advantage of notably more flexibility in downstream classification tasks.