Semantic Description of Explainable Machine Learning Workflows for Improving Trust
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,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/22/10804 |
| _version_ | 1797511269111037952 |
|---|---|
| author | Patricia Inoue Nakagawa Luís Ferreira Pires João Luiz Rebelo Moreira Luiz Olavo Bonino da Silva Santos Faiza Bukhsh |
| author_facet | Patricia Inoue Nakagawa Luís Ferreira Pires João Luiz Rebelo Moreira Luiz Olavo Bonino da Silva Santos Faiza Bukhsh |
| author_sort | Patricia Inoue Nakagawa |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T05:43:55Z |
| format | Article |
| id | doaj.art-21fbc5b1d44846b3b8fe4a7daa3cd927 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T05:43:55Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-21fbc5b1d44846b3b8fe4a7daa3cd9272023-11-22T22:19:09ZengMDPI AGApplied Sciences2076-34172021-11-0111221080410.3390/app112210804Semantic Description of Explainable Machine Learning Workflows for Improving TrustPatricia Inoue Nakagawa0Luís Ferreira Pires1João Luiz Rebelo Moreira2Luiz Olavo Bonino da Silva Santos3Faiza Bukhsh4Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS), University of Twente, 7522 NB Enschede, The NetherlandsFaculty of Electrical Engineering, Mathematics and Computer Science (EEMCS), University of Twente, 7522 NB Enschede, The NetherlandsFaculty of Electrical Engineering, Mathematics and Computer Science (EEMCS), University of Twente, 7522 NB Enschede, The NetherlandsFaculty of Electrical Engineering, Mathematics and Computer Science (EEMCS), University of Twente, 7522 NB Enschede, The NetherlandsFaculty of Electrical Engineering, Mathematics and Computer Science (EEMCS), University of Twente, 7522 NB Enschede, The NetherlandsExplainable 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.https://www.mdpi.com/2076-3417/11/22/10804XAImachine learningsemantic web technologiesontology |
| spellingShingle | Patricia Inoue Nakagawa Luís Ferreira Pires João Luiz Rebelo Moreira Luiz Olavo Bonino da Silva Santos Faiza Bukhsh Semantic Description of Explainable Machine Learning Workflows for Improving Trust Applied Sciences XAI machine learning semantic web technologies ontology |
| title | Semantic Description of Explainable Machine Learning Workflows for Improving Trust |
| title_full | Semantic Description of Explainable Machine Learning Workflows for Improving Trust |
| title_fullStr | Semantic Description of Explainable Machine Learning Workflows for Improving Trust |
| title_full_unstemmed | Semantic Description of Explainable Machine Learning Workflows for Improving Trust |
| title_short | Semantic Description of Explainable Machine Learning Workflows for Improving Trust |
| title_sort | semantic description of explainable machine learning workflows for improving trust |
| topic | XAI machine learning semantic web technologies ontology |
| url | https://www.mdpi.com/2076-3417/11/22/10804 |
| work_keys_str_mv | AT patriciainouenakagawa semanticdescriptionofexplainablemachinelearningworkflowsforimprovingtrust AT luisferreirapires semanticdescriptionofexplainablemachinelearningworkflowsforimprovingtrust AT joaoluizrebelomoreira semanticdescriptionofexplainablemachinelearningworkflowsforimprovingtrust AT luizolavoboninodasilvasantos semanticdescriptionofexplainablemachinelearningworkflowsforimprovingtrust AT faizabukhsh semanticdescriptionofexplainablemachinelearningworkflowsforimprovingtrust |