OnML: an ontology-based approach for interpretable machine learning

Document Type

Article

Publication Date

8-1-2022

Abstract

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.

Identifier

85128881928 (Scopus)

Publication Title

Journal of Combinatorial Optimization

External Full Text Location

https://doi.org/10.1007/s10878-022-00856-z

e-ISSN

15732886

ISSN

13826905

First Page

770

Last Page

793

Issue

1

Volume

44

Grant

CNS-1850094

Fund Ref

University of Oregon

This document is currently not available here.

Share

COinS