XPROAX-Local explanations for text classification with progressive neighborhood approximation

TL;DR

This paper introduces XPROAX, a novel method for generating local explanations for text classifiers by progressively approximating neighborhoods with counterfactuals and factuals, improving explanation quality and stability.

Contribution

It proposes a two-stage sampling approach using counterfactuals as landmarks to better generate neighborhoods for textual explanations, addressing high-dimensional challenges.

Findings

Outperforms competitors in usefulness and stability

Achieves better completeness, compactness, and correctness

Effective for real-world text classification datasets

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).