All Models are Wrong but many are Useful: Variable Importance for Black-Box, Proprietary, or Misspecified Prediction Models, using Model Class Reliance

By Aaron Fisher, Cynthia Rudin, Francesca Dominici. 2018

128 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

Machine learning and deep learning—A review for ecologists (2022, methodology): “Global xAI methods try to summarize the models by generating variable importance (similar to the natural variable importances from RF and BRT; Fisher et al., 2018 ) or simplify the models by approximating the original model with interpretable models (Molnar, 2020 ).”
Trustworthy Artificial Intelligence: A Review (2022, methodology): “In-the-loop 3 Interpretable Model Global [40, 87, 120] Feature Importance Local [161] Global, Local [9, 66, 77, 93, 127, 227]”
The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies (2020, background): “Alternatively, Feature Importance [44] measures the increase in”
Variable Importance Clouds: A Way to Explore Variable Importance for the Set of Good Models (2019, methodology): “Model reliance function MR in Definition 2.3 turns out to have a specific formula for ridge regression models, given by the lemma below, which is a generalization of Theorem 2 of Fisher et al. (2018) to ridge regression.”
GNNExplainer: Generating Explanations for Graph Neural Networks (2019, background): “Instead of creating new, inherently interpretable models, post-hoc interpretability methods [1, 14, 15, 17, 23, 38] consider models as black boxes and then probe them for relevant information.”
Legal requirements on explainability in machine learning (2020, unknown): “1 3 perturbing feature values to assess the importance of each feature used in a model can in fact be extrapolated and applied to any machine learning algorithm (Fisher et al. 2018).”
The Secrets of Machine Learning: Ten Things You Wish You Had Known Earlier to be More Effective at Data Analysis (2019, background): “that race is a causal factor for recidivism [16].”