The LCFI website uses cookies only for anonymised website statistics and for ensuring our security, never for tracking or identifying you individually. To find out more, and to find out how we protect your personal information, please read our privacy policy.

Evaluating and Aggregating Feature-based Model Explanations

Conference Paper by Umang Bhatt, Adrian Weller, Jose M. F. Moura

Evaluating and Aggregating Feature-based Model ExplanationsInternational Joint Conference on Artificial Intelligence (IJCAI-PRICAI), 2020.

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.

Download Conference Paper