Feature Importance
Feature Importance is a model interpretability metric that quantifies the contribution of individual input features to a machine learning model's predictions, distinguishing itself from other interpretability methods by focusing on the relative influence of features rather than their functional relationships or causal mechanisms.
2.9K
Publications
181.9K
Citations
10K
Authors
3K
Institutions
Publications per year
2017–2026
2K
Parents
2.9K
A Unified Approach to Interpreting Model Predictions
Scott Lundberg, Su‐In Lee · arXiv (Cornell University) · 2017 · 7.6K citations · Full text
Conditional variable importance for random forests
Carolin Strobl, Anne‐Laure Boulesteix, Thomas Kneib et al. · BMC Bioinformatics · 2008 · 3.2K citations · Full text
Permutation importance: a corrected feature importance measure
André Altmann, Laura Toloşi, Oliver Sander et al. · Bioinformatics · 2010 · 2.7K citations · Full text
1–5 of 2.9K
10K
8
h-index
8
h-index
8
h-index
8
h-index
8
h-index
1–5 of 10K
3K

Chinese Academy of Sciences
Beijing, China
27 h-index
158 publications
12.9K citations
Stanford University
Stanford, United States
20 h-index
71 publications
7.7K citations
Nanyang Technological University
Singapore, Singapore
19 h-index
55 publications
5K citations
Harvard University
Cambridge, United States
18 h-index
75 publications
6.3K citations
University of Chinese Academy of Sciences
Beijing, China
18 h-index
67 publications
5.5K citations
University of Washington
Seattle, United States
18 h-index
44 publications
45.4K citations

Zhejiang University
Hangzhou, China
17 h-index
46 publications
5.3K citations

Hong Kong Polytechnic University
Hong Kong, Hong Kong
17 h-index
32 publications
2.2K citations
1–8 of 3K
Repository · 114 publications · 16.4K citations
42
h-index
68 publications · 3.2K citations
34
h-index
53 publications · 2.9K citations
29
h-index
40 publications · 1.4K citations
25
h-index
24 publications · 1K citations
20
h-index
1–5