The Library
CHILLI : a data context-aware perturbation method for XAI
Tools
Anwar, Saif, Griffiths, Nathan, Bhalerao, Abhir, Popham, T. J., Bell, Mark and Hellman, Shaun (2023) CHILLI : a data context-aware perturbation method for XAI. In: ICML Workshop on Artificial Intelligence and Human-Computer Interaction, Honolulu, Hawaii, USA, 29 Jul 2023. Published in: Proceedings of the 40th International Conference on Machine Learning, 202 ISSN 2640-3498. (In Press)
|
PDF
WRAP-CHILLI-data-context-aware-perturbation-method-XAI-2023.pdf - Accepted Version - Requires a PDF viewer. Download (726Kb) | Preview |
Abstract
The trustworthiness of Machine Learning (ML) models can be difficult to assess, but is critical in high-risk or ethically sensitive applications. Many models are treated as a ‘black-box’ where the reasoning or criteria for a final decision is opaque to the user. To address this, some existing Explainable AI (XAI) approaches approximate model behaviour using perturbed data. However, such methods have been criticised for ignoring feature dependencies, with explanations being based on potentially unrealistic data. We propose a novel framework, CHILLI, for incorporating data context into XAI by generating contextually aware perturbations, which are faithful to the training data of the base model being explained. This is shown to improve both the soundness and accuracy of the explanations.
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software |
||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||
Library of Congress Subject Headings (LCSH): | Machine Learning, Artificial intelligence, Computational intelligence, Data mining | ||||||
Series Name: | Proceedings of Machine Learning Research | ||||||
Journal or Publication Title: | Proceedings of the 40th International Conference on Machine Learning | ||||||
ISSN: | 2640-3498 | ||||||
Official Date: | 2023 | ||||||
Dates: |
|
||||||
Volume: | 202 | ||||||
Status: | Peer Reviewed | ||||||
Publication Status: | In Press | ||||||
Access rights to Published version: | Free Access (unspecified licence, 'bronze OA') | ||||||
Date of first compliant deposit: | 22 June 2023 | ||||||
Date of first compliant Open Access: | 23 June 2023 | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | ICML Workshop on Artificial Intelligence and Human-Computer Interaction | ||||||
Type of Event: | Workshop | ||||||
Location of Event: | Honolulu, Hawaii, USA | ||||||
Date(s) of Event: | 29 Jul 2023 | ||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year