Year: 2020
Type: preprint
Abstract: Understanding the inner workings of complex machine learning models is a long-standing problem and most recent research has focused on local interpretability. To assess the role of individual input features in a global sense, we explore the perspective of defining feature importance through the predictive power associated with each feature. We introduce two notions of predictive power (model-based and universal) and formalize this approach with a framework of additive importance measures, which unifies numerous methods in the literature. We then propose SAGE, a model-agnostic method that quantifies predictive power while accounting for feature interactions. Our experiments show that SAGE can be calculated efficiently and that it assigns more accurate importance values than other methods.
Source: arXiv (Cornell University)
Authors: Covert, Ian, Lundberg, Scott, Lee, Su-In
Institutions: University of Washington, Microsoft (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3014290757
