arXiv:2504.10169cs.LGstat.ML2025-04被引 4
揭示加性模型的可解释性陷阱，提醒勿过度信赖其透明性
Challenges in interpretability of additive models
- 指出加性模型存在多种不可识别性问题
- 强调其可解释性在实际中常被夸大
- 适合关注模型可信度的研究者与安全应用开发者
我们回顾了广义加性模型作为一种近期在深度学习领域重新受到关注的‘透明’模型，即神经加性模型。本文指出了该模型类别中存在的多种不可识别性问题，并讨论了其可解释性面临的挑战，主张在宣称此类模型具备‘可解释性’或‘适用于安全关键应用’时应保持谨慎。
原文摘要 · Abstract (English)
We review generalized additive models as a type of ``transparent'' model that has recently seen renewed interest in the deep learning community as neural additive models. We highlight multiple types of nonidentifiability in this model class and discuss challenges in interpretability, arguing for restraint when claiming ``interpretability'' or ``suitability for safety-critical applications'' of such models.
可解释性模型可信度加性模型
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。