mlsanityData to 7 Oct 2026

Classification using Hyperdimensional Computing: A Review

arXiv 2004.11204 ↗First posted 19 Apr 2020cs.LG cs.AI cs.CLcited by 60

Not on the map. Why?

Abstract (arXiv)

Hyperdimensional (HD) computing is built upon its unique data type referred to as hypervectors. The dimension of these hypervectors is typically in the range of tens of thousands. Proposed to solve cognitive tasks, HD computing aims at calculating similarity among its data. Data transformation is realized by three operations, including addition, multiplication and permutation. Its ultra-wide data representation introduces redundancy against noise. Since information is evenly distributed over every bit of the hypervectors, HD computing is inherently robust. Additionally, due to the nature of those three operations, HD computing leads to fast learning ability, high energy efficiency and acceptable accuracy in learning and classification tasks. This paper introduces the background of HD computing, and reviews the data representation, data transformation, and similarity measurement. The orthogonality in high dimensions presents opportunities for flexible computing. To balance the tradeoff between accuracy and efficiency, strategies include but are not limited to encoding, retraining, binarization and hardware acceleration. Evaluations indicate that HD computing shows great potential in addressing problems using data in the form of letters, signals and images. HD computing especially shows significant promise to replace machine learning algorithms as a light-weight classifier in the field of internet of things (IoTs).

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 11; 2023: 14; 2024: 11; 2025: 8; 2026: 5.

60 papers.

Sort:

By area:

  1. 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformationscited by 98
  2. 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challengescited by 68
  3. 2021Vector Symbolic Architectures as a Computing Framework for Emerging Hardwarecited by 35
  4. 2022Understanding Hyperdimensional Computing for Parallel Single-Pass Learningcited by 20
  5. 2022LeHDC: Learning-Based Hyperdimensional Computing Classifiercited by 17
  6. 2022Torchhd: An Open Source Python Library to Support Research on Hyperdimensional Computing and Vector Symbolic Architecturescited by 17
  7. 2021Hypervector Design for Efficient Hyperdimensional Computing on Edge Devicescited by 16
  8. 2021Hyperdimensional Feature Fusion for Out-Of-Distribution Detectioncited by 13
  9. 2023DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classificationcited by 13
  10. 2021Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional Computingcited by 12
  11. 2022A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devicescited by 11
  12. 2023On-Device Unsupervised Image Segmentationcited by 10
38 more
  1. 2021Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networkscited by 7
  2. 2023Learning from Hypervectors: A Survey on Hypervector Encodingcited by 7
  3. 2021A 5 μ W Standard Cell Memory-based Configurable Hyperdimensional Computing Accelerator for Always-on Smart Sensingcited by 6
  4. 2024Generalized Holographic Reduced Representationscited by 6
  5. 2023DOMINO: Domain-invariant Hyperdimensional Classification for Multi-Sensor Time Series Datacited by 5
  6. 2024Hyperdimensional Representation Learning for Node Classification and Link Predictioncited by 5
  7. 2021Shift-Equivariant Similarity-Preserving Hypervector Representations of Sequencescited by 4
  8. 2022An Extension to Basis-Hypervectors for Learning from Circular Data in Hyperdimensional Computingcited by 4
  9. 2024Laplace-HDC: Understanding the geometry of binary hyperdimensional computingcited by 4
  10. 2022Automated Architecture Search for Brain-inspired Hyperdimensional Computingcited by 3
  11. 2022Streaming Encoding Algorithms for Scalable Hyperdimensional Computingcited by 3
  12. 2023MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaptioncited by 3
  13. 2023Training a HyperDimensional Computing Classifier using a Threshold on its Confidencecited by 3
  14. 2023Resource-Efficient Federated Hyperdimensional Computingcited by 3
  15. 2023Sobol Sequence Optimization for Hardware-Efficient Vector Symbolic Architecturescited by 3
  16. 2024HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoningcited by 3
  17. 2022Recursive Binding for Similarity-Preserving Hypervector Representations of Sequencescited by 2
  18. 2023The Hyperdimensional Transform for Distributional Modelling, Regression and Classificationcited by 2
  19. 2024Hyperdimensional computing: a fast, robust and interpretable paradigm for biological datacited by 2
  20. 2025HD-CB: The First Exploration of Hyperdimensional Computing for Contextual Bandits Problemscited by 2
  21. 2025DecoHD: Decomposed Hyperdimensional Classification under Extreme Memory Budgetscited by 2
  22. 2025LogHD: Robust Compression of Hyperdimensional Classifiers via Logarithmic Class-Axis Reductioncited by 2
  23. 2021Brain-inspired Cognition in Next Generation Racetrack Memoriescited by 1
  24. 2023uHD: Unary Processing for Lightweight and Dynamic Hyperdimensional Computingcited by 1
  25. 2024Molecular Classification Using Hyperdimensional Graph Classificationcited by 1
  26. 2024Enhanced Detection of Transdermal Alcohol Levels Using Hyperdimensional Computing on Embedded Devicescited by 1
  27. 2024Scheduled Knowledge Acquisition on Lightweight Vector Symbolic Architectures for Brain-Computer Interfacescited by 1
  28. 2024On Design Choices in Similarity-Preserving Sparse Randomized Embeddingscited by 1
  29. 2025FactorHD: A Hyperdimensional Computing Model for Multi-Object Multi-Class Representation and Factorizationcited by 1
  30. 2021HDXplore: Automated Blackbox Testing of Brain-Inspired Hyperdimensional Computingcited by 0
  31. 2022Brain-Inspired Hyperdimensional Computing: How Thermal-Friendly for Edge Computing?cited by 0
  32. 2022Computing with Hypervectors for Efficient Speaker Identificationcited by 0
  33. 2022NasHD: Efficient ViT Architecture Performance Ranking using Hyperdimensional Computingcited by 0
  34. 2023HD-Bind: Encoding of Molecular Structure with Low Precision, Hyperdimensional Binary Representationscited by 0
  35. 2023HyperSNN: A new efficient and robust deep learning model for resource constrained control applicationscited by 0
  36. 2023Towards Efficient Hyperdimensional Computing Using Photonicscited by 0
  37. 2023Robust Clustering using Hyperdimensional Computingcited by 0
  38. 2024CiliaGraph: Enabling Expression-enhanced Hyper-Dimensional Computation in Ultra-Lightweight and One-Shot Graph Classification on Edgecited by 0

50 most cited of 60 All 60 (JSON)