Global Explanations
Global Explanations is a type of model-agnostic interpretability method that characterizes the overall behavior of a machine learning model across its entire input domain, distinguishing itself from local explanations by providing comprehensive insights into global decision patterns rather than instance-specific predictions.
112
Publications
16.2K
Citations
416
Authors
178
Institutions
Publications per year
2017–2026
98
Variants
Global Interpretability
112
From local explanations to global understanding with explainable AI for trees
Scott Lundberg, Gabriel Erion, Hugh Chen et al. · Nature Machine Intelligence · 2020 · 8.9K citations · Full text
Explainability for Large Language Models: A Survey
Haiyan Zhao, Hanjie Chen, Fan Yang et al. · ACM Transactions on Intelligent Systems and Technology · 2024 · 544 citations · Full text
An Explainable Machine Learning Framework for Intrusion Detection Systems
Maonan Wang, Kangfeng Zheng, Yanqing Yang et al. · IEEE Access · 2020 · 321 citations · Full text
1–5 of 112
416
4
h-index
3
h-index
3
h-index
3
h-index
3
h-index
1–5 of 416
178

University of Pisa
Pisa, Italy
4 h-index
16 publications
2.1K citations
University of Cambridge
Cambridge, United Kingdom
4 h-index
10 publications
409 citations
University of Washington
Seattle, United States
3 h-index
14 publications
89.5K citations
Carnegie Mellon University
Pittsburgh, United States
3 h-index
8 publications
212 citations

Harvard University Press
Cambridge, United States
2 h-index
2 publications
36 citations

The University of Melbourne
Melbourne, Australia
2 h-index
6 publications
303 citations
Northwestern University
Evanston, United States
2 h-index
2 publications
36 citations
NetEase (China)
Beijing, China
2 h-index
16 publications
548 citations
1–8 of 178
Repository · 26 publications · 933 citations
16
h-index
Conference · 5 publications · 330 citations
5
h-index
Repository · 4 publications · 137 citations
4
h-index
3 publications · 263 citations
3
h-index
3 publications · 476 citations
3
h-index
1–5