Function (biology)

Algorithm

Linguistics

Engineering

Philosophy

Biology

Materials science

Aggregate (composite)

Data mining

Computer science

Evolutionary biology

Mathematics

Value (mathematics)

Feature (linguistics)

Electronic engineering

Artificial intelligence

Geometry

Composite material

Sensitivity (control systems)

Mathematical economics

Point (geometry)

Game theory

Shapley value

Machine learning

A feature-based model explanation denotes how much each input feature contributes to a model's output for a given data point. As the number of proposed explanation functions grows, we lack quantitative evaluation criteria to help practitioners know when to use which explanation function. This paper proposes quantitative evaluation criteria for feature-based explanations: low sensitivity, high faithfulness, and low complexity. We devise a framework for aggregating explanation functions. We develop a procedure for learning an aggregate explanation function with lower complexity and then derive a new aggregate Shapley value explanation function that minimizes sensitivity.

Evaluating and Aggregating Feature-based Model Explanations