TY - GEN
T1 - Constraints-based explanations of classifications
AU - Deutch, Daniel
AU - Frost, Nave
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/4
Y1 - 2019/4
N2 - A main component of many Data Science applications is the invocation of Machine Learning (ML) classifiers. The typical complexity of these classification models makes it difficult to understand the reason for a result, and consequently to assess its trustworthiness and detect errors. We propose a simple generic approach for explaining classifications, by identifying relevant parts of the input whose perturbation would be significant in affecting the classification. In contrast to previous work, our solution makes use of constraints over the data, to guide the search for meaningful explanations in the application domain. Constraints may either be derived from the schema or specified by a domain expert for the purpose of computing explanations. We have implemented the approach for prominent ML models such as Random Forests and Neural Networks. We demonstrate, through examples and experiments, the effectiveness of our solution, and in particular of its novel use of constraints.
AB - A main component of many Data Science applications is the invocation of Machine Learning (ML) classifiers. The typical complexity of these classification models makes it difficult to understand the reason for a result, and consequently to assess its trustworthiness and detect errors. We propose a simple generic approach for explaining classifications, by identifying relevant parts of the input whose perturbation would be significant in affecting the classification. In contrast to previous work, our solution makes use of constraints over the data, to guide the search for meaningful explanations in the application domain. Constraints may either be derived from the schema or specified by a domain expert for the purpose of computing explanations. We have implemented the approach for prominent ML models such as Random Forests and Neural Networks. We demonstrate, through examples and experiments, the effectiveness of our solution, and in particular of its novel use of constraints.
KW - Data provenance
KW - Database constraints theory
KW - Supervised learning by classification
UR - http://www.scopus.com/inward/record.url?scp=85067929345&partnerID=8YFLogxK
U2 - 10.1109/ICDE.2019.00054
DO - 10.1109/ICDE.2019.00054
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85067929345
T3 - Proceedings - International Conference on Data Engineering
SP - 530
EP - 541
BT - Proceedings - 2019 IEEE 35th International Conference on Data Engineering, ICDE 2019
PB - IEEE Computer Society
T2 - 35th IEEE International Conference on Data Engineering, ICDE 2019
Y2 - 8 April 2019 through 11 April 2019
ER -