2026-04-21T04:45:24Zhttps://ebiltegia.mondragon.edu/oai/request

oai:ebiltegia.mondragon.edu:20.500.11984/60662024-03-04T12:12:51Zcom_20.500.11984_473col_20.500.11984_478

Real-Time, Model-Agnostic and User-Driven Counterfactual Explanations Using Autoencoders Labaien Soto, Jokin Zugasti, Ekhi De Carlos Garcia, Xabier explainable AI autoencoders counterfactual explanations 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. 2023-03-28T18:03:20Z 2023-03-28T18:03:20Z 2023 http://purl.org/coar/resource_type/c_6501 2076-3417 https://katalogoa.mondragon.edu/janium-bin/janium_login_opac.pl?find&ficha_no=172008 https://hdl.handle.net/20.500.11984/6066 eng Attribution 4.0 International http://creativecommons.org/licenses/by/4.0/ © 2023 The Authors MDPI