Title
Real-Time, Model-Agnostic and User-Driven Counterfactual Explanations Using AutoencodersAuthor (from another institution)
xmlui.dri2xhtml.METS-1.0.item-contributorOtherinstitution
https://ror.org/03hp1m080Version
http://purl.org/coar/version/c_970fb48d4fbd8a85
Rights
© 2023 The AuthorsAccess
http://purl.org/coar/access_right/c_abf2Publisher’s version
https://doi.org/10.3390/app13052912Published at
Applied Sciences Vol. 13. N. 5. N. artículo 2912Publisher
MDPIKeywords
explainable AIautoencoders
counterfactual explanations
Abstract
Explainable Artificial Intelligence (XAI) has gained significant attention in recent years due to concerns over the lack of interpretability of Deep Learning models, which hinders their decision-makin ... [+]
Explainable Artificial Intelligence (XAI) has gained significant attention in recent years due to concerns over the lack of interpretability of Deep Learning models, which hinders their decision-making processes. To address this issue, counterfactual explanations have been proposed to elucidate the reasoning behind a model’s decisions by providing what-if statements as explanations. However, generating counterfactuals traditionally involves solving an optimization problem for each input, making it impractical for real-time feedback. Moreover, counterfactuals must meet specific criteria, including being user-driven, causing minimal changes, and staying within the data distribution. To overcome these challenges, a novel model-agnostic approach called Real-Time Guided Counterfactual Explanations (RTGCEx) is proposed. This approach utilizes autoencoders to generate real-time counterfactual explanations that adhere to these criteria by optimizing a multiobjective loss function. The performance of RTGCEx has been evaluated on two datasets: MNIST and Gearbox, a synthetic time series dataset. The results demonstrate that RTGCEx outperforms traditional methods in terms of speed and efficacy on MNIST, while also effectively identifying and rectifying anomalies in the Gearbox dataset, highlighting its versatility across different scenarios. [-]
xmlui.dri2xhtml.METS-1.0.item-sponsorship
Gobierno Vasco-Eusko Jaurlaritzaxmlui.dri2xhtml.METS-1.0.item-projectID
info:eu-repo/grantAgreement/GV/Elkartek 2022/KK-2022-00049/CAPV/Deeplearning REcomendation Manufacturing Imperfection Novelty Detection/DREMINDCollections
- Articles - Engineering [639]
The following license files are associated with this item: