用反事实解释增强星系分类模型，让预测结果更可懂。
Galaxy Morphology Classification with Counterfactual Explanation
- 在编码器-解码器架构中引入可逆流，实现可解释性增强。
- 在星系形态分类任务上达到高准确率，同时生成反事实解释。
- 适合需要理解模型决策过程的天文学研究者使用。
星系形态在星系演化研究中至关重要。面对海量数据，人工判断形态耗时费力，因此采用基于机器学习的方法成为主流。然而，大多数现有方法缺乏对模型内部运作机制的解释，导致结果难以理解和信任。本文提出在经典编码器-解码器架构中引入可逆流（invertible flow），不仅保持了良好的预测性能，还能够提供关于决策过程的反事实解释，揭示哪些特征变化会导致分类结果改变。该方法提升了模型的可解释性，有助于天文学家理解模型判断依据。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。