交互式工具SAInT用敏感性分析帮用户理解模型决策逻辑。
A Visual Tool for Interactive Model Explanation using Sensitivity Analysis
- 通过图形界面实现无需编程的模型训练与解释
- 结合全局敏感性分析与局部解释方法（LIME/SHAP）
- 适合研究人员和领域专家用于模型调试与数据优化
我们提出SAInT，一个基于Python的可视化工具，通过集成局部与全局敏感性分析，帮助用户理解机器学习模型的行为。该系统支持人机协同工作流，使AI研究人员和领域专家可通过交互式图形界面配置、训练、评估和解释模型，无需编程。工具自动完成模型训练与选择，利用基于方差的敏感性分析提供全局特征重要性，同时通过LIME和SHAP提供单个样本的解释。我们在泰坦尼克号生存预测任务上展示了该系统，说明敏感性信息可指导特征选择与数据优化。
原文摘要 · Abstract (English)
We present SAInT, a Python-based tool for visually exploring and understanding the behavior of Machine Learning (ML) models through integrated local and global sensitivity analysis. Our system supports Human-in-the-Loop (HITL) workflows by enabling users - both AI researchers and domain experts - to configure, train, evaluate, and explain models through an interactive graphical interface without programming. The tool automates model training and selection, provides global feature attribution using variance-based sensitivity analysis, and offers per-instance explanation via LIME and SHAP. We demonstrate the system on a classification task predicting survival on the Titanic dataset and show how sensitivity information can guide feature selection and data refinement.
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。