Auditing Black-Box Models Using Transparent Model Distillation With Side Information

By Sarah Tan, R. Caruana, Giles Hooker, Yin Lou. 2017

18 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Sarah Tan
2. R. Caruana
3. Xuezhou Zhang
4. Paul Koch
5. Yin Lou
6. Cynthia Rudin
7. Giles Hooker
8. Urszula Chajewska

Citations in the corpus

• Improving Simple Models with Confidence Profiles (2018, unknown): “This approach, unlike Distillation [14, 26, 30], is applicable in broader settings like when target models are classifiers optimized using empirical risk (e.g., SVM) where risk could be any loss function.”
• Interpretability is Harder in the Multiclass Setting: Axiomatic Interpretability for Multiclass Additive Models (2018, background): “In criminal justice, finance, hiring, and other domains that impact people’s lives, interpretable models are often used because their transparency helps determine if a model is biased or unsafe (Zeng, Ustun, and Rudin 2016; Tan et al. 2017).”