TY - GEN
T1 - GRACE
T2 - 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2020
AU - Le, Thai
AU - Wang, Suhang
AU - Lee, Dongwon
N1 - Funding Information:
8 ACKNOWLEDGEMENT This work was in part supported by NSF awards #1742702, #1820609, #1909702, #1915801 and #1934782. We appreciate anonymous reviewers for all of their constructive comments.
Publisher Copyright:
© 2020 ACM.
PY - 2020/8/23
Y1 - 2020/8/23
N2 - Despite the recent development in the topic of explainable AI/ML for image and text data, the majority of current solutions are not suitable to explain the prediction of neural network models when the datasets are tabular and their features are in high-dimensional vectorized formats. To mitigate this limitation, therefore, we borrow two notable ideas (i.e., "explanation by intervention" from causality and "explanation are contrastive" from philosophy) and propose a novel solution, named as GRACE, that better explains neural network models' predictions for tabular datasets. In particular, given a model's prediction as label X, GRACE intervenes and generates a minimally-modified contrastive sample to be classified as Y, with an intuitive textual explanation, answering the question of "Why X rather than Y?" We carry out comprehensive experiments using eleven public datasets of different scales and domains (e.g., # of features ranges from 5 to 216) and compare GRACE with competing baselines on different measures: fidelity, conciseness, info-gain, and influence. The user-studies show that our generated explanation is not only more intuitive and easy-to-understand but also facilitates end-users to make as much as 60% more accurate post-explanation decisions than that of Lime.
AB - Despite the recent development in the topic of explainable AI/ML for image and text data, the majority of current solutions are not suitable to explain the prediction of neural network models when the datasets are tabular and their features are in high-dimensional vectorized formats. To mitigate this limitation, therefore, we borrow two notable ideas (i.e., "explanation by intervention" from causality and "explanation are contrastive" from philosophy) and propose a novel solution, named as GRACE, that better explains neural network models' predictions for tabular datasets. In particular, given a model's prediction as label X, GRACE intervenes and generates a minimally-modified contrastive sample to be classified as Y, with an intuitive textual explanation, answering the question of "Why X rather than Y?" We carry out comprehensive experiments using eleven public datasets of different scales and domains (e.g., # of features ranges from 5 to 216) and compare GRACE with competing baselines on different measures: fidelity, conciseness, info-gain, and influence. The user-studies show that our generated explanation is not only more intuitive and easy-to-understand but also facilitates end-users to make as much as 60% more accurate post-explanation decisions than that of Lime.
UR - http://www.scopus.com/inward/record.url?scp=85090409699&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090409699&partnerID=8YFLogxK
U2 - 10.1145/3394486.3403066
DO - 10.1145/3394486.3403066
M3 - Conference contribution
AN - SCOPUS:85090409699
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 238
EP - 248
BT - KDD 2020 - Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PB - Association for Computing Machinery
Y2 - 23 August 2020 through 27 August 2020
ER -