Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics

Zhou, J; Gandomi, AH; Chen, F; Holzinger, A

Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics

Zhou, J

Gandomi, AH Chen, F Holzinger, A

Permalink

Publisher:: MDPI AG
Publication Type:: Journal Article
Citation:: Electronics, 10, (5), pp. 593-593

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (7.52 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zhou, J https://orcid.org/0000-0001-6034-644X
dc.contributor.author	Gandomi, AH
dc.contributor.author	Chen, F
dc.contributor.author	Holzinger, A
dc.date.accessioned	2021-03-10T00:18:30Z
dc.date.available	2021-03-10T00:18:30Z
dc.identifier.citation	Electronics, 10, (5), pp. 593-593
dc.identifier.issn	2079-9292
dc.identifier.uri	http://hdl.handle.net/10453/146976
dc.description.abstract	<jats:p>The most successful Machine Learning (ML) systems remain complex black boxes to end-users, and even experts are often unable to understand the rationale behind their decisions. The lack of transparency of such systems can have severe consequences or poor uses of limited valuable resources in medical diagnosis, financial decision-making, and in other high-stake domains. Therefore, the issue of ML explanation has experienced a surge in interest from the research community to application domains. While numerous explanation methods have been explored, there is a need for evaluations to quantify the quality of explanation methods to determine whether and to what extent the offered explainability achieves the defined objective, and compare available explanation methods and suggest the best explanation from the comparison for a specific task. This survey paper presents a comprehensive overview of methods proposed in the current literature for the evaluation of ML explanations. We identify properties of explainability from the review of definitions of explainability. The identified properties of explainability are used as objectives that evaluation metrics should achieve. The survey found that the quantitative metrics for both model-based and example-based explanations are primarily used to evaluate the parsimony/simplicity of interpretability, while the quantitative metrics for attribution-based explanations are primarily used to evaluate the soundness of fidelity of explainability. The survey also demonstrated that subjective measures, such as trust and confidence, have been embraced as the focal point for the human-centered evaluation of explainable systems. The paper concludes that the evaluation of ML explanations is a multidisciplinary research topic. It is also not possible to define an implementation of evaluation metrics, which can be applied to all explanation methods.</jats:p>
dc.language	en
dc.publisher	MDPI AG
dc.relation.ispartof	Electronics
dc.relation.isbasedon	10.3390/electronics10050593
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0906 Electrical and Electronic Engineering
dc.title	Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics
dc.type	Journal Article
utslib.citation.volume	10
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/A/DRsch The Data Science Institute
utslib.copyright.status	open_access	*
dc.date.updated	2021-03-10T00:18:28Z
pubs.issue	5
pubs.publication-status	Published online
pubs.volume	10
utslib.citation.issue	5

Abstract:

The most successful Machine Learning (ML) systems remain complex black boxes to end-users, and even experts are often unable to understand the rationale behind their decisions. The lack of transparency of such systems can have severe consequences or poor uses of limited valuable resources in medical diagnosis, financial decision-making, and in other high-stake domains. Therefore, the issue of ML explanation has experienced a surge in interest from the research community to application domains. While numerous explanation methods have been explored, there is a need for evaluations to quantify the quality of explanation methods to determine whether and to what extent the offered explainability achieves the defined objective, and compare available explanation methods and suggest the best explanation from the comparison for a specific task. This survey paper presents a comprehensive overview of methods proposed in the current literature for the evaluation of ML explanations. We identify properties of explainability from the review of definitions of explainability. The identified properties of explainability are used as objectives that evaluation metrics should achieve. The survey found that the quantitative metrics for both model-based and example-based explanations are primarily used to evaluate the parsimony/simplicity of interpretability, while the quantitative metrics for attribution-based explanations are primarily used to evaluate the soundness of fidelity of explainability. The survey also demonstrated that subjective measures, such as trust and confidence, have been embraced as the focal point for the human-centered evaluation of explainable systems. The paper concludes that the evaluation of ML explanations is a multidisciplinary research topic. It is also not possible to define an implementation of evaluation metrics, which can be applied to all explanation methods.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/146976