In EDS ansehen

Improving Local Fidelity and Interpretability of LIME by Replacing Only the Sampling Process With CVAE

Gespeichert in:
Bibliographische Detailangaben
Titel: Improving Local Fidelity and Interpretability of LIME by Replacing Only the Sampling Process With CVAE
Autoren: Daisuke Yasui, Hiroshi Sato
Quelle: IEEE Access, Vol 13, Pp 53084-53099 (2025)
Verlagsinformationen: Institute of Electrical and Electronics Engineers (IEEE), 2025.
Publikationsjahr: 2025
Schlagwörter: local fidelity, conditional variational autoencoder, Electrical engineering. Electronics. Nuclear engineering, LIME, interpretability, TK1-9971
Beschreibung: Knowing the basis of decisions is essential for using Machine Learning (ML) in various regions, such as medical diagnosis, finance, and organizational decision-making. The Local Interpretable Model agnostic Explanation (LIME) algorithm is an Explainable AI (XAI) method that can be applied to many black -box models. However, there is a problem in that the local fidelity of the interpretable model decreases. Therefore, local fidelity must be increased, and the more interpretability of the local surrogate model, the better. Moreover, the fewer the changes, the easier it is to apply them to other studies and the more significant the contribution to the XAI area. Therefore, there are studies that improve fidelity by changing only the sampling. However, no studies have been identified that improve local fidelity and interpretability by modifying only the sampling. To this end, we use a conditional variational autoencoder (CVAE) to modify the sampling of LIME in the classification task to improve local fidelity and interpretability. We conducted a study to improve local fidelity and interpretability by modifying only the sampling part and clarifying the mechanism behind this improvement. Results show that the proposed method improves local fidelity while increasing interpretability compared to existing methods and the factors contributing to this improvement. We also conducted experiments on stability, stability against noise, and execution time, and confirmed that the proposed method performs well, although not as well as methods specific to these issues. Our code is publicly released on GitHub (https://github.com/YasuiDaisuke/CVAE-LIME.git) under the Apache 2.0 License.
Publikationsart: Article
ISSN: 2169-3536
DOI: 10.1109/access.2025.3553505
Zugangs-URL: https://doaj.org/article/d01705e7b3f54a5c8f2cb42f42a57459
Rights: CC BY NC ND
Dokumentencode: edsair.doi.dedup.....c0833c6f5eba6bbce0a54c1aab9d19f5
Datenbank: OpenAIRE
Beschreibung
Abstract:Knowing the basis of decisions is essential for using Machine Learning (ML) in various regions, such as medical diagnosis, finance, and organizational decision-making. The Local Interpretable Model agnostic Explanation (LIME) algorithm is an Explainable AI (XAI) method that can be applied to many black -box models. However, there is a problem in that the local fidelity of the interpretable model decreases. Therefore, local fidelity must be increased, and the more interpretability of the local surrogate model, the better. Moreover, the fewer the changes, the easier it is to apply them to other studies and the more significant the contribution to the XAI area. Therefore, there are studies that improve fidelity by changing only the sampling. However, no studies have been identified that improve local fidelity and interpretability by modifying only the sampling. To this end, we use a conditional variational autoencoder (CVAE) to modify the sampling of LIME in the classification task to improve local fidelity and interpretability. We conducted a study to improve local fidelity and interpretability by modifying only the sampling part and clarifying the mechanism behind this improvement. Results show that the proposed method improves local fidelity while increasing interpretability compared to existing methods and the factors contributing to this improvement. We also conducted experiments on stability, stability against noise, and execution time, and confirmed that the proposed method performs well, although not as well as methods specific to these issues. Our code is publicly released on GitHub (https://github.com/YasuiDaisuke/CVAE-LIME.git) under the Apache 2.0 License.
ISSN:21693536
DOI:10.1109/access.2025.3553505