Semantic Description of Explainable Machine Learning Workflows for Improving Trust
Source abstract
Abstract
Explainable Machine Learning comprises methods and techniques that enable users to better understand the machine learning functioning and results. This work proposes an ontology that represents explainable machine learning experiments, allowing data scientists and developers to have a holistic view, a better understanding of the explainable machine learning process, and to build trust. We developed the ontology by reusing an existing domain-specific ontology (ML-SCHEMA) and grounding it in the Unified Foundational Ontology (UFO), aiming at achieving interoperability. The proposed ontology is structured in three modules: (1) the general module, (2) the specific module, and (3) the explanation module. The ontology was evaluated using a case study in the scenario of the COVID-19 pandemic using healthcare data from patients, which are sensitive data. In the case study, we trained a Support Vector Machine to predict mortality of patients infected with COVID-19 and applied existing explanation methods to generate explanations from the trained model. Based on the case study, we populated the ontology and queried it to ensure that it fulfills its intended purpose and to demonstrate its suitability.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Explainable Artificial Intelligence (XAI) · Machine Learning in Healthcare · Artificial Intelligence in Healthcare and Education
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS), University of Twente, 7522 NB Enschede, The Netherlands
References (35)
Show source-provided references
1. Seeliger, A., Pfaff, M., and Krcmar, H. (2019, January 27). Semantic Web Technologies for Explainable Machine Learning Models: A Literature Review. Proceedings of the Joint Proceedings of the 6th International Workshop on Dataset PROFlLing and Search & the 1st Workshop on Semantic Explainability co-located with the 18th International Semantic Web Conference (ISWC 2019), Auckland, New Zealand.
2. The Challenge of Crafting Intelligible Intelligence10.1145/3282486 ↗
3. Ribeiro, M., Singh, S., and Guestrin, C. (2016, January 12–17). “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, San Diego, CA, USA.10.18653/v1/N16-3020 ↗
4. Doran, D., Schulz, S., and Besold, T. (2017, January 16–17). What does explainable AI really mean? A new conceptualization of perspectives. Proceedings of the First International Workshop on Comprehensibility and Explanation in AI and ML 2017 Co-Located with 16th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2017), Bari, Italy.
5. Holzinger, A., Biemann, C., Pattichis, C.S., and Kell, D.B. (2017). What do we need to build explainable AI systems for the medical domain?. arXiv.
6. Holzinger, A., Kieseberg, P., Weippl, E., and Tjoa, A. (2018). Current advances, trends and challenges of machine learning and knowledge extraction: From machine learning to explainable AI. Machine Learning and Knowledge Extraction, Springer International Publishing. Lecture Notes in Computer Science.10.1007/978-3-319-99740-7_1 ↗
7. Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)10.1109/ACCESS.2018.2870052 ↗
8. Holzinger, A., Kieseberg, P., Tjoa, A., and Weippl, E. (2020). Explainable Artificial Intelligence: Concepts, Applications, Research Challenges and Visions. Machine Learning and Knowledge Extraction, Springer International Publishing. Lecture Notes in Computer Science.10.1007/978-3-030-57321-8 ↗
9. Dignum, V. (2019). Responsible Artificial Intelligence: How to Develop and Use AI in a Responsible Way, Springer.10.1007/978-3-030-30371-6 ↗
10. Mikolajczyk, A., Grochowski, M., and Kwasigroch, A. (2020). Towards explainable classifiers using the counterfactual approach—Global explanations for discovering bias in data. arXiv.10.2478/jaiscr-2021-0004 ↗
11. Chander, A., and Srinivasan, R. (2019). Creation of User Friendly Datasets: Insights from a Case Study concerning Explanations of Loan Denials. arXiv.
12. Domingue, J., Fensel, D., and Hendler, J. (2011). Handbook of Semantic Web Technology, Springer.10.1007/978-3-540-92913-0 ↗
13. Falbo, R.A. (2014, January 21). SABiO: Systematic approach for building ontologies. Proceedings of the 1st Joint Workshop ONTO.COM/ODISE on Ontologies in Conceptual Modeling and Information Systems Engineering, Rio de Janeiro, Brazil.
14. Esteves, D., Ławrynowicz, A., Panov, P., Soldatova, L., Soru, T., and Vanschoren, J. (2021, February 01). ML Schema Core Specification, 17 October 2016. Available online: http://ml-schema.github.io/documentation/ML%20Schema.html.
15. Fernández, M., Gómez-Pérez, A., and Juristo, N. (2021, September 30). Methontology: From ontological art towards ontological engineering. AAAI Technical Report. Available online: https://www.researchgate.net/publication/50236211_METHONTOLOGY_from_ontological_art_towards_ontological_engineering.
16. Guizzardi, G., and Wagner, G. (2004, January 7–11). A Unified Foundational Ontology and some Applications of it in Business Modeling. Proceedings of the CAiSE’04 Workshops in Connection with the 16th Conference on Advanced Information Systems Engineering, Knowledge and Model Driven Information Systems Engineering for Networked Organisations, Riga, Latvia.
17. Guizzardi, G., Wagner, G., Falbo, R., Guizzardi, R., and Almeida, J. (2013). Towards Ontological Foundations for the Conceptual Modeling of Events. Conceptual Modeling, Springer.10.1007/978-3-642-41924-9_27 ↗
18. Almeida, J.P.A., Falbo, R., Guizzardi, G., and Sales, T.P. (2021, April 10). gUFO: A Lightweight Implementation of the Unified Foundational Ontology (UFO). Available online: http://purl.org/nemo/doc/gufo.
19. OntoUML Community (2021, April 10). OntoUML Specification. Available online: https://ontouml.readthedocs.io/en/latest/intro/ontouml.html.
20. Fonseca, C.M., Sales, T.P., Bassetti, L., and Viola, V. (2021, May 12). OntoUML Plugin for Visual Paradigm, May 2021. Available online: https://github.com/OntoUML/ontouml-vp-plugin.
21. The Data Mining OPtimization Ontology10.1016/j.websem.2015.01.001 ↗
22. Franklin, M.R. (2021, March 09). Kaggle: Mexico COVID-19 Clinical Data, 6 May 2020. Available online: https://www.kaggle.com/marianarfranklin/mexico-COVID19-clinical-data/metadata.
23. Cohen, W.W. (1995, January 9–12). Fast effective rule induction. Proceedings of the Twelfth International Conference on Machine Learning, Tahoe City, CA, USA.
24. Martens, D., Huysmans, J., Setiono, R., and Vanthienen, J. (2008). Rule Extraction from Support Vector Machines: An Overview of Issues and Application in Credit Scoring. Studies in Computational Intelligence, Springer.10.1007/978-3-540-75390-2_2 ↗
25. Molnar, C. (2020, November 09). Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. Available online: https://christophm.github.io/interpretable-ml-book.
26. Linardatos, P., Papastefanopoulos, V., and Kotsiantis, S. (2021). Explainable AI: A Review of Machine Learning Interpretability Methods. Entropy, 23.10.3390/e23010018 ↗
27. (2021, March 10). Ethical Institute, XAI—An Explainability Toolbox for Machine Learning. Available online: https://github.com/EthicalML/xai.
28. Machine learning based approaches for detecting COVID-19 using clinical text data
29. Machine learning prediction for mortality of patients diagnosed with COVID 19: A nationwide Korean cohort study10.1038/s41598-020-75767-2 ↗
30. An Explainable System for Diagnosis and Prognosis of COVID-1910.1109/JIOT.2020.3037915 ↗
31. Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: A Feasibility Study10.1007/s10916-020-01597-4 ↗
32. A machine learning model to identify early stage symptoms of SARS-Cov-2 infected patients10.1016/j.eswa.2020.113661 ↗
33. Scikit-learn: Machine learning in Python
34. Moscovitz, I. (2021, February 05). Wittgenstein, 19 May 2020. Available online: https://github.com/imoscovitz/wittgenstein.
35. Barcellos, L.C., Batista, J.O., and Almeida, J.P.A. (2021, April 16). UFO Validation for Protégé, 23 November 2020. Available online: https://github.com/nemo-ufes/ufo-protege-plugin.