XPROAX-Local explanations for text classification with progressive neighborhood approximation
Yi Cai, Arthur Zimek, Eirini Ntoutsi – 2021
The importance of the neighborhood for training a local surrogate model to approximate the local decision boundary of a black box classifier has been already highlighted in the literature. Several attempts have been made to construct a better neighborhood for high dimensional data, like texts, by using generative autoencoders. However, existing approaches mainly generate neighbors by selecting purely at random from the latent space and struggle under the curse of dimensionality to learn a good local decision boundary.
Title
XPROAX-Local explanations for text classification with progressive neighborhood approximation
Author
Yi Cai, Arthur Zimek, Eirini Ntoutsi
Keywords
Explainable AI, Local explanations, Counterfactuals, Neighborhood approximation, Text classification
Date
2021-07
Identifier
DOI: 10.1109/DSAA53316.2021.9564153
Source(s)
Appeared in
Proceedings of the 8th IEEE International Conference on Data Science and Advanced Analytics (DSAA) (to appear)
Language
eng
Type
Text
Size or Duration
10 pages