Projects per year
Abstract
Explanations in Machine Learning come in many forms, but a consensus regarding their desired properties is yet to emerge. In this paper we introduce a taxonomy and a set of descriptors that can be used to characterise and systematically assess explainable systems along five key dimensions: functional, operational, usability, safety and validation. In order to design a comprehensive and representative taxonomy and associated descriptors we surveyed the eXplainable Artificial Intelligence literature, extracting the criteria and desiderata that other authors have proposed or implicitly used in their research. The survey includes papers introducing new explainability algorithms to see what criteria are used to guide their development and how these algorithms are evaluated, as well as papers proposing such criteria from both computer science and social science perspectives. This novel framework allows to systematically compare and contrast explainability approaches, not just to better understand their capabilities but also to identify discrepancies between their theoretical qualities and properties of their implementations. We developed an operationalisation of the framework in the form of Explainability Fact Sheets, which enable researchers and practitioners alike to quickly grasp capabilities and limitations of a particular explainable method. When used as a Work Sheet, our taxonomy can guide the development of new explainability approaches by aiding in their critical evaluation along the five proposed dimensions.
Original language | English |
---|---|
Title of host publication | FAT* 2020 - Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency |
Publisher | Association for Computing Machinery (ACM) |
Pages | 56-67 |
Number of pages | 12 |
ISBN (Electronic) | 9781450369367 |
DOIs | |
Publication status | Published - 27 Jan 2020 |
Event | 3rd ACM Conference on Fairness, Accountability, and Transparency, FAT* 2020 - Barcelona, Spain Duration: 27 Jan 2020 → 30 Jan 2020 |
Publication series
Name | FAT* 2020 - Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency |
---|
Conference
Conference | 3rd ACM Conference on Fairness, Accountability, and Transparency, FAT* 2020 |
---|---|
Country/Territory | Spain |
City | Barcelona |
Period | 27/01/20 → 30/01/20 |
Research Groups and Themes
- Digital Health
- SPHERE
Keywords
- AI
- Desiderata
- Explainability
- Fact Sheet
- Interpretability
- ML
- Taxonomy
- Transparency
- Work Sheet
Fingerprint
Dive into the research topics of 'Explainability fact sheets: A framework for systematic assessment of explainable approaches'. Together they form a unique fingerprint.Projects
- 1 Finished
-
SPHERE2
Craddock, I. J. (Principal Investigator), Mirmehdi, M. (Co-Investigator), Piechocki, R. J. (Co-Investigator), Flach, P. A. (Co-Investigator), Oikonomou, G. (Co-Investigator), Burghardt, T. (Co-Investigator), Damen, D. (Co-Investigator), Santos-Rodriguez, R. (Co-Investigator), O'Kane, A. A. (Co-Investigator), McConville, R. (Co-Investigator), Masullo, A. (Co-Investigator) & Gooberman-Hill, R. (Co-Investigator)
1/10/18 → 31/01/23
Project: Research, Parent