Learning Global Additive Explanations for Neural Nets Using Model Distillation

By Sarah Tan, R. Caruana, Giles Hooker, Paul Koch, Albert Gordo. 2018

112 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.

Citations in the corpus

FEED: Feature-level Ensemble for Knowledge Distillation (2019, background): “This motivated researchers to develop many variants of it to various domains, and many researchers studied ways to better teach the student (Frosst and Hinton 2017; Pham et al. 2018; Radosavovic et al. 2018; Tan et al. 2018; Tarvainen and Valpola 2017).”
"Why Should You Trust My Explanation?" Understanding Uncertainty in LIME Explanations (2019, methodology): “…inherently interpretable models (Letham et al., 2015; Lakkaraju et al., 2016), and creating post-hoc methods to explain black-box models, either locally around a speciﬁc input (Baehrens et al., 2010; Ribeiro et al., 2016) or globally for the entire model (Ribeiro et al., 2018a; Tan et al., 2018a).”
Interpreting Interpretability: Understanding Data Scientists' Use of Interpretability Tools for Machine Learning (2020, unknown): “[57] test the feasibility of a new GAM-based blackbox explainability approach with ML experts across various publicly available datasets.”
Feature-Level Ensemble Knowledge Distillation for Aggregating Knowledge from Multiple Networks (2020, background): “This motivated researchers to develop many variants of it to various domains, and many researchers studied ways to better teach the student [6, 18, 19, 24, 25].”
Please Stop Permuting Features: An Explanation and Alternatives (2019, methodology): “Tan et al. (2018) found that these better represented the over-all behavior of the function than methods based on combining local explanations.”
Human-Centered Explainable AI (XAI): From Algorithms to User Experiences (2021, methodology): “For example, a technique called distillation changes the learning objective of the interpretable model to match the original model’s predictions [95].”