Signatures to help interpretability of anomalies
Machine Learning
2025-06-23 v1 Instrumentation and Methods for Astrophysics
Abstract
Machine learning is often viewed as a black box when it comes to understanding its output, be it a decision or a score. Automatic anomaly detection is no exception to this rule, and quite often the astronomer is left to independently analyze the data in order to understand why a given event is tagged as an anomaly. We introduce here idea of anomaly signature, whose aim is to help the interpretability of anomalies by highlighting which features contributed to the decision.
Cite
@article{arxiv.2506.16314,
title = {Signatures to help interpretability of anomalies},
author = {Emmanuel Gangler and Emille E. O. Ishida and Matwey V. Kornilov and Vladimir Korolev and Anastasia Lavrukhina and Konstantin Malanchev and Maria V. Pruzhinskaya and Etienne Russeil and Timofey Semenikhin and Sreevarsha Sreejith and Alina A. Volnova},
journal= {arXiv preprint arXiv:2506.16314},
year = {2025}
}
Comments
7 pages, 3 figure, proceedings of the International Conference on Machine Learning for Astrophysics (ML4ASTRO2)