C-Eval: A Unified Metric to Evaluate Feature-based Explanations via Perturbation
Document Type
Conference Proceeding
Publication Date
1-1-2021
Abstract
In many image-classification applications, understanding the reasons of model's prediction can be as critical as the prediction's accuracy itself. Various feature-based local explainers have been designed to provide explanations on the decision of complex classifiers. Nevertheless, there is no consensus on evaluating the quality of different explanations. In response to this lack of comprehensive evaluation, we introduce the c-Eval metric and its corresponding framework to quantify the feature-based local explanation's quality. Given a classifier's prediction and the corresponding explanation on that prediction, c-Eval is the minimum-distortion perturbation that successfully alters the prediction while keeping the explanation's features unchanged. To show that c-Eval captures the importance of input's features, we establish a connection between c-Eval and the features returned by explainers in affine and nearly-affine classifiers. We then introduce the c-Eval plot, which not only displays a strong connection between c-Eval and explainers' quality, but also helps automatically determine explainer's parameters.
Identifier
85125326364 (Scopus)
ISBN
[9781665439022]
Publication Title
Proceedings 2021 IEEE International Conference on Big Data Big Data 2021
External Full Text Location
https://doi.org/10.1109/BigData52589.2021.9671895
First Page
927
Last Page
937
Grant
1939725
Recommended Citation
Vu, Minh N.; Nguyen, Truc D.; Phan, Nhat Hai; Gera, Ralucca; and Thai, My T., "C-Eval: A Unified Metric to Evaluate Feature-based Explanations via Perturbation" (2021). Faculty Publications. 4547.
https://digitalcommons.njit.edu/fac_pubs/4547