改进积分梯度的基线设计，让模型解释更可信
Constructing sensible baselines for Integrated Gradients
- 用背景事件均值作为基线，替代零向量
- 新基线使特征重要性分配更合理，减少偏差
- 适合需要可信解释的科学领域模型分析
机器学习在科学领域的应用迅猛增长，但对其“黑箱”特性的理解仍不足。本文以粒子物理为例，探讨如何通过设计不同基线来应用积分梯度（IGs）以理解模型。研究发现，使用零向量作为基线会生成不合理特征贡献，而从背景事件中采样得到的平均基线则能持续提供更合理的归因结果。
原文摘要 · Abstract (English)
Machine learning methods have seen a meteoric rise in their applications in the scientific community. However, little effort has been put into understanding these "black box" models. We show how one can apply integrated gradients (IGs) to understand these models by designing different baselines, by taking an example case study in particle physics. We find that the zero-vector baseline does not provide good feature attributions and that an averaged baseline sampled from the background events provides consistently more reasonable attributions.
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。