hdlib 2.0: Extending Machine Learning Capabilities of Vector-Symbolic Architectures

2026-01-05

arXiv.org

AI Summary

This work addresses the limited support of existing Vector Symbolic Architectures (VSAs) for data-driven machine learning tasks such as regression, clustering, and graph learning. Building upon hdlib, the study introduces the first quantum hyperdimensional computing framework that integrates quantum arithmetic with quantum machine learning, thereby extending VSA capabilities to four core domains: supervised classification, regression, clustering, and graph representation learning. The authors present the first open-source, multi-task VSA library equipped with a comprehensive toolchain, publicly released via GitHub, PyPI, and Conda. This contribution significantly broadens the applicability and practical utility of hyperdimensional computing in artificial intelligence.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Visual Reasoning & Symbolic Representations
• Cognitive Modeling & Cognitive Systems: Symbolic Representations

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Following the initial publication of hdlib, a Python library for designing Vector-Symbolic Architectures (VSA), we introduce a major extension that significantly enhances its machine learning capabilities. VSA, also known as Hyperdimensional Computing, is a computing paradigm that represents and processes information using high-dimensional vectors. While the first version of hdlib established a robust foundation for creating and manipulating these vectors, this update addresses the growing need for more advanced, data-driven modeling within the VSA framework. Here, we present four extensions: significant enhancements to the existing supervised classification model also enabling feature selection, and a new regression model for predicting continuous variables, a clustering model for unsupervised learning, and a graph-based learning model. Furthermore, we propose the first implementation ever of Quantum Hyperdimensional Computing with quantum-powered arithmetic operations and a new Quantum Machine Learning model for supervised learning. hdlib remains open-source and available on GitHub at https://github.com/cumbof/hdlib under the MIT license, and distributed through the Python Package Index (pip install hdlib) and Conda (conda install -c conda-forge hdlib). Documentation and examples of these new features are available on the official Wiki at https://github.com/cumbof/hdlib/wiki.

Problem

• Vector-Symbolic Architectures
• Hyperdimensional Computing
• Machine Learning
• Quantum Hyperdimensional Computing
• Data-driven Modeling

Innovation

• Vector-Symbolic Architectures
• Hyperdimensional Computing
• Quantum Machine Learning
• Supervised Classification
• Unsupervised Clustering