XPROAX-Local explanations for text classification with progressive neighborhood approximation

Abstract

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. To overcome this problem, we propose a progressive approximation of the neighborhood using counterfactual instances as initial landmarks and a careful 2-stage sampling approach to refine counterfactuals and generate factuals in the neighborhood of the input instance to be explained. Our work focuses on textual data and our explanations consist of both word-level explanations from the original instance (intrinsic) and the neighborhood (extrinsic) and factual- and counterfactual-instances discovered during the neighborhood generation process that further reveal the effect of altering certain parts in the input text. Our experiments on real-world datasets demonstrate that our method outperforms the competitors in terms of usefulness and stability (for the qualitative part) and completeness, compactness and correctness (for the quantitative part).

arXiv commentIEEE DSAA '21

References in corpus (11)

• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Predictive learning via rule ensembles
• Style Transfer from Non-Parallel Text by Cross-Alignment
• Diversity in Machine Learning
• A Survey of the State of Explainable AI for Natural Language Processing
• Local Rule-Based Explanations of Black Box Decision Systems
• Model Agnostic Supervised Local Explanations
• On the Robustness of Interpretability Methods
• Defining Locality for Surrogates in Post-hoc Interpretablity
• Explaining Predictions by Approximating the Local Decision Boundary