{"ID":2854630,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.14655","arxiv_id":"2510.14655","title":"Galaxy Morphology Classification with Counterfactual Explanation","abstract":"Galaxy morphologies play an essential role in the study of the evolution of galaxies. The determination of morphologies is laborious for a large amount of data giving rise to machine learning-based approaches. Unfortunately, most of these approaches offer no insight into how the model works and make the results difficult to understand and explain. We here propose to extend a classical encoder-decoder architecture with invertible flow, allowing us to not only obtain a good predictive performance but also provide additional information about the decision process with counterfactual explanations.","short_abstract":"Galaxy morphologies play an essential role in the study of the evolution of galaxies. The determination of morphologies is laborious for a large amount of data giving rise to machine learning-based approaches. Unfortunately, most of these approaches offer no insight into how the model works and make the results difficu...","url_abs":"https://arxiv.org/abs/2510.14655","url_pdf":"https://arxiv.org/pdf/2510.14655v1","authors":"[\"Zhuo Cao\",\"Lena Krieger\",\"Hanno Scharr\",\"Ira Assent\"]","published":"2025-10-16T13:11:56Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}