Explaining individual predictions when features are dependent: More accurate approximations to Shapley values
Work
Year: 2021
Type: article
Abstract: Explaining complex or seemingly simple machine learning models is an important practical problem. We want to explain individual predictions from such models by learning simple, interpretable explanati... more
Source: Artificial Intelligence
Authors Kjersti Aas, Martin Jullum, Anders Løland
Institution Norwegian Computing Center
Cites: 54
Cited by: 443
Related to: 10
FWCI: 44.79
Citation percentile (by year/subfield): 100
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Sustainable Development Goal Reduced inequalities
Open Access status: hybrid
APC paid (est): $3,670
Funder Norges Forskningsråd
Grant ID 237718