一种用于异常解释性的签名
机器学习
2025-06-23 v1 天体物理仪器与方法
摘要
机器学习常被视为黑箱，难以理解其输出是决策还是评分。自动异常检测亦是如此，常常让天文学家独立分析数据以理解某一事件为何被标记为异常。我们在此提出异常签名（anomaly signature）的概念，旨在帮助解释异常，通过突出显示哪些特征Contributing to decision。
引用
@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}
}
备注
7 pages, 3 figure, proceedings of the International Conference on Machine Learning for Astrophysics (ML4ASTRO2)