Evaluating and Aggregating Feature-Based Model Explanations
Abstract
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.
Cite
Text
Bhatt et al. "Evaluating and Aggregating Feature-Based Model Explanations." International Joint Conference on Artificial Intelligence, 2020. doi:10.24963/IJCAI.2020/417Markdown
[Bhatt et al. "Evaluating and Aggregating Feature-Based Model Explanations." International Joint Conference on Artificial Intelligence, 2020.](https://mlanthology.org/ijcai/2020/bhatt2020ijcai-evaluating/) doi:10.24963/IJCAI.2020/417BibTeX
@inproceedings{bhatt2020ijcai-evaluating,
title = {{Evaluating and Aggregating Feature-Based Model Explanations}},
author = {Bhatt, Umang and Weller, Adrian and Moura, José M. F.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2020},
pages = {3016-3022},
doi = {10.24963/IJCAI.2020/417},
url = {https://mlanthology.org/ijcai/2020/bhatt2020ijcai-evaluating/}
}