TY - JOUR
T1 - OnML
T2 - an ontology-based approach for interpretable machine learning
AU - Ayranci, Pelin
AU - Lai, Phung
AU - Phan, Nhathai
AU - Hu, Han
AU - Kolinowski, Alexander
AU - Newman, David
AU - Dou, Deijing
N1 - Funding Information:
The authors gratefully acknowledge the support from the National Science Foundation (NSF) Grant Nos. CNS-1747798, CNS-1850094, and NSF Center for Big Learning (Oregon). We thank for the financial support from Wells Fargo. We also thank Nisansa de Silva (University of Oregon, USA) for valuable discussions and Anuja Badeti (New Jersey Institute of Technology, USA) for helping with data processing. Pelin Ayranci and Phung Lai are co-first authors.
Funding Information:
The authors gratefully acknowledge the support from the National Science Foundation (NSF) Grant Nos. CNS-1747798, CNS-1850094, and NSF Center for Big Learning (Oregon). We thank for the financial support from Wells Fargo. We also thank Nisansa de Silva (University of Oregon, USA) for valuable discussions and Anuja Badeti (New Jersey Institute of Technology, USA) for helping with data processing. Pelin Ayranci and Phung Lai are co-first authors.
Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2022/8
Y1 - 2022/8
N2 - In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models. Different from existing approaches, our interpretable algorithm considers contextual correlation among words, described in domain knowledge ontologies, to generate semantic explanations. To narrow down the search space for explanations, which is exponentially large given long and complicated text data, we design a learnable anchor algorithm to better extract local and domain knowledge-oriented explanations. A set of regulations is further introduced, combining learned interpretable representations with anchors and information extraction to generate comprehensible semantic explanations. To carry out an extensive experiment, we first develop a drug abuse ontology (DAO) on a drug abuse dataset on the Twittersphere, and a consumer complaint ontology (ConsO) on a consumer complaint dataset, especially for interpretable ML. Our experimental results show that our approach generates more precise and more insightful explanations compared with a variety of baseline approaches.
AB - In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models. Different from existing approaches, our interpretable algorithm considers contextual correlation among words, described in domain knowledge ontologies, to generate semantic explanations. To narrow down the search space for explanations, which is exponentially large given long and complicated text data, we design a learnable anchor algorithm to better extract local and domain knowledge-oriented explanations. A set of regulations is further introduced, combining learned interpretable representations with anchors and information extraction to generate comprehensible semantic explanations. To carry out an extensive experiment, we first develop a drug abuse ontology (DAO) on a drug abuse dataset on the Twittersphere, and a consumer complaint ontology (ConsO) on a consumer complaint dataset, especially for interpretable ML. Our experimental results show that our approach generates more precise and more insightful explanations compared with a variety of baseline approaches.
KW - Anchor
KW - Information extraction
KW - Interpretable machine learning
KW - Ontology
UR - http://www.scopus.com/inward/record.url?scp=85128881928&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85128881928&partnerID=8YFLogxK
U2 - 10.1007/s10878-022-00856-z
DO - 10.1007/s10878-022-00856-z
M3 - Article
AN - SCOPUS:85128881928
SN - 1382-6905
VL - 44
SP - 770
EP - 793
JO - Journal of Combinatorial Optimization
JF - Journal of Combinatorial Optimization
IS - 1
ER -