Explaining and interpreting hyperdimensional computing classifiers on tabular data

2025/09/25 by Laura Smets, Werner Van Leekwijck, Steven Latré +1 · 1 voice
Engineering · Materials Science · #Ferroelectric and Negative Capacitance Devices #Advanced Memory and Neural Computing #Electronic and Structural Properties of Oxides

paper · doi:10.1016/j.neucom.2025.131643

openalex publication_date 2025/09/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/06/20

Abstract

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.

Citations

• Holographic reduced representations
• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations
• Hyperdimensional computing: a fast, robust and interpretable paradigm for biological data
• A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices
• HDC-MiniROCKET: Explicit Time Encoding in Time Series Classification with Hyperdimensional Computing
• Shift-Equivariant Similarity-Preserving Hypervector Representations of Sequences
• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges
• Memory-Efficient, Limb Position-Aware Hand Gesture Recognition using Hyperdimensional Computing
• Sanity Checks for Saliency Maps
• RISE: Randomized Input Sampling for Explanation of Black-box Models
• Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks
• Hyper-dimensional computing for a visual question-answering system that is trainable end-to-end
• A Unified Approach to Interpreting Model Predictions
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
• "Why Should I Trust You?": Explaining the Predictions of Any Classifier
• Vector Symbolic Architectures answer Jackendoff's challenges for cognitive neuroscience

Discussions

• Our work on Interpretable #Hyperdimensional Computing (HDC) classifiers for #tabular data is now available at #Neurocomputing. doi.org/10.1016/j.ne... #Neuromorphic #interpretability #Explainability [bsky, 1 points, 1 comments]

Related

• MAIRE -- A Model-Agnostic Interpretable Rule Extraction Procedure for\n Explaining Classifiers
• LeHDC: Learning-Based Hyperdimensional Computing Classifier
• HyConEx: Hypernetwork classifier with counterfactual explanations
• Explaining high-dimensional text classifiers
• Interpretable classifiers for tabular data via discretization and feature selection