Causal Dependence Plots

arXiv (Cornell University)(2023)

引用 1|浏览2
暂无评分
摘要
Explaining artificial intelligence or machine learning models is increasingly important. To use such data-driven systems wisely we must understand how they interact with the world, including how they depend causally on data inputs. In this work we develop Causal Dependence Plots (CDPs) to visualize how one variable--an outcome--depends on changes in another variable--a predictor--$\textit{along with any consequent causal changes in other predictor variables}$. Crucially, CDPs differ from standard methods based on holding other predictors constant or assuming they are independent. CDPs make use of an auxiliary causal model because causal conclusions require causal assumptions. With simulations and real data experiments, we show CDPs can be combined in a modular way with methods for causal learning or sensitivity analysis. Since people often think causally about input-output dependence, CDPs can be powerful tools in the xAI or interpretable machine learning toolkit and contribute to applications like scientific machine learning and algorithmic fairness.
更多
查看译文
关键词
causal
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要