TY - GEN
T1 - Explaining A Black-box By Using A Deep Variational Information Bottleneck Approach
AU - Bang, Seojin
AU - Xie, Pengtao
AU - Lee, Heewook
AU - Wu, Wei
AU - Xing, Eric
N1 - Funding Information: This work was supported by the grants P30DA035778 and R01GM140467 from the NIH, and Petuum Inc.. Publisher Copyright: Copyright © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2021
Y1 - 2021
N2 - Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiveness simultaneously, leading to redundant explanations. We propose the variational information bottleneck for interpretation, VIBI, a system-agnostic interpretable method that provides a brief but comprehensive explanation. VIBI adopts an information theoretic principle, information bottleneck principle, as a criterion for finding such explanations. For each instance, VIBI selects key features that are maximally compressed about an input (briefness), and informative about a decision made by a black-box system on that input (comprehensive). We evaluate VIBI on three datasets and compare with state-of-the-art interpretable machine learning methods in terms of both interpretability and fidelity evaluated by human and quantitative metrics.
AB - Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiveness simultaneously, leading to redundant explanations. We propose the variational information bottleneck for interpretation, VIBI, a system-agnostic interpretable method that provides a brief but comprehensive explanation. VIBI adopts an information theoretic principle, information bottleneck principle, as a criterion for finding such explanations. For each instance, VIBI selects key features that are maximally compressed about an input (briefness), and informative about a decision made by a black-box system on that input (comprehensive). We evaluate VIBI on three datasets and compare with state-of-the-art interpretable machine learning methods in terms of both interpretability and fidelity evaluated by human and quantitative metrics.
UR - http://www.scopus.com/inward/record.url?scp=85126364630&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126364630&partnerID=8YFLogxK
M3 - Conference contribution
T3 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
SP - 11396
EP - 11404
BT - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
PB - Association for the Advancement of Artificial Intelligence
T2 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
Y2 - 2 February 2021 through 9 February 2021
ER -