MASALA: Model-Agnostic Surrogate Explanations by Locality Adaptation

TL;DR

MASALA is a novel local XAI method that automatically identifies impactful regions for each prediction, providing more faithful and consistent explanations without needing user-defined locality hyperparameters.

Contribution

It introduces MASALA, a new approach that adapts the local explanation region automatically, improving explanation fidelity and consistency over existing methods like LIME and CHILLI.

Findings

MASALA outperforms LIME and CHILLI in fidelity and consistency.

It eliminates the need for locality hyperparameter tuning.

Experiments on PHM08 and MIDAS datasets validate its effectiveness.

Abstract

Existing local Explainable AI (XAI) methods, such as LIME, select a region of the input space in the vicinity of a given input instance, for which they approximate the behaviour of a model using a simpler and more interpretable surrogate model. The size of this region is often controlled by a user-defined locality hyperparameter. In this paper, we demonstrate the difficulties associated with defining a suitable locality size to capture impactful model behaviour, as well as the inadequacy of using a single locality size to explain all predictions. We propose a novel method, MASALA, for generating explanations, which automatically determines the appropriate local region of impactful model behaviour for each individual instance being explained. MASALA approximates the local behaviour used by a complex model to make a prediction by fitting a linear surrogate model to a set of points which experience similar model behaviour. These points are found by clustering the input space into regions of linear behavioural trends exhibited by the model. We compare the fidelity and consistency of explanations generated by our method with existing local XAI methods, namely LIME and CHILLI. Experiments on the PHM08 and MIDAS datasets show that our method produces more faithful and consistent explanations than existing methods, without the need to define any sensitive locality hyperparameters.