GAM Coach: Towards Interactive and User-centered Algorithmic Recourse

要旨

Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed. However, a recourse plan's actionability is subjective and unlikely to match developers' expectations completely. We present GAM Coach, a novel open-source system that adapts integer linear programming to generate customizable counterfactual explanations for Generalized Additive Models (GAMs), and leverages interactive visualizations to enable end users to iteratively generate recourse plans meeting their needs. A quantitative user study with 41 participants shows our tool is usable and useful, and users prefer personalized recourse plans over generic plans. Through a log analysis, we explore how users discover satisfactory recourse plans, and provide empirical evidence that transparency can lead to more opportunities for everyday users to discover counterintuitive patterns in ML models. GAM Coach is available at: https://poloclub.github.io/gam-coach/.

著者
Zijie J.. Wang
Georgia Tech, Atlanta, Georgia, United States
Jennifer Wortman Vaughan
Microsoft Research, New York, New York, United States
Rich Caruana
Microsoft Research, Redmond, Washington, United States
Duen Horng Chau
Georgia Tech, Atlanta, Georgia, United States
論文URL

https://doi.org/10.1145/3544548.3580816

動画

会議: CHI 2023

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2023.acm.org/)

セッション: Visualization for AI/ML

Room X11+X12
6 件の発表
2023-04-25 01:35:00
2023-04-25 03:00:00