Explaining and interpreting hyperdimensional computing classifiers on tabular data

Given the rise in the usage of artificial intelligence models and machine learning approaches in our day-to-day lives, it has become increasingly important to explain these models to increase user trust. Hyperdimensional Computing (HDC) has been introduced as a powerful, energy-efficient algorithmic framework that is intrinsically less opaque than (deep) neural networks. Nevertheless, the possibility of explaining and interpreting the HDC-based classification model has not yet been explored explicitly. Therefore, this work proposes an explanation method and an interpretation method for the HDC-based classification model working with tabular data. The proposed methods have been successfully evaluated on three tabular data sets with a diverse number of samples, features, and classes. Their faithfulness is validated with coherence checks, the deletion and insertion metrics, and a feature ablation study. The results of the proposed explanation method align well with the well-studied LIME explanations. • An explanation and an interpretation method are proposed for HDC on tabular data. • The methods are fast as they employ HDC’s efficient arithmetic vector operations. • The methods are faithful, validated with coherence checks and ablation studies. • The deletion and insertion metrics are adjusted to apply to the HDC classifier.