OnML: an ontology-based approach for interpretable machine learning

Pelin Ayranci, Phung Lai, Nhathai Phan, Han Hu, Alexander Kolinowski, David Newman, Deijing Dou

Research output: Contribution to journalArticlepeer-review

4 Scopus citations


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.

Original languageEnglish (US)
Pages (from-to)770-793
Number of pages24
JournalJournal of Combinatorial Optimization
Issue number1
StatePublished - Aug 2022

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Discrete Mathematics and Combinatorics
  • Control and Optimization
  • Computational Theory and Mathematics
  • Applied Mathematics


  • Anchor
  • Information extraction
  • Interpretable machine learning
  • Ontology


Dive into the research topics of 'OnML: an ontology-based approach for interpretable machine learning'. Together they form a unique fingerprint.

Cite this