期刊
IEEE ACCESS
卷 9, 期 -, 页码 11974-12001出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3051315
关键词
Cognition; Artificial intelligence; Training; Terminology; Taxonomy; Systematics; Signal to noise ratio; Computational intelligence; contrastive explanations; counterfactuals; explainable artificial intelligence; systematic literature review
资金
- Spanish Ministry of Science, Innovation and Universities [RTI2018-099646-B-I00, RED2018-102641-T]
- Galician Ministry of Education, University and Professional Training [ED431F 2018/02, ED431C 2018/29, ED431G/08, ED431G2019/04]
- European Regional Development Fund (ERDF/FEDER Program)
This study presents a systematic literature review on contrastive and counterfactual explanations in artificial intelligence algorithms, examining theoretical foundations and computational frameworks. The research reveals shortcomings in existing approaches and proposes a taxonomy for theoretical and practical methods in contrastive and counterfactual explanation.
A number of algorithms in the field of artificial intelligence offer poorly interpretable decisions. To disclose the reasoning behind such algorithms, their output can be explained by means of so-called evidence-based (or factual) explanations. Alternatively, contrastive and counterfactual explanations justify why the output of the algorithms is not any different and how it could be changed, respectively. It is of crucial importance to bridge the gap between theoretical approaches to contrastive and counterfactual explanation and the corresponding computational frameworks. In this work we conduct a systematic literature review which provides readers with a thorough and reproducible analysis of the interdisciplinary research field under study. We first examine theoretical foundations of contrastive and counterfactual accounts of explanation. Then, we report the state-of-the-art computational frameworks for contrastive and counterfactual explanation generation. In addition, we analyze how grounded such frameworks are on the insights from the inspected theoretical approaches. As a result, we highlight a variety of properties of the approaches under study and reveal a number of shortcomings thereof. Moreover, we define a taxonomy regarding both theoretical and practical approaches to contrastive and counterfactual explanation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据