paper-with-me

Papers

Tensor Products and Hyperdimensional Computing

2023-05-17 · Frank Qiu

Following up on a previous analysis of graph embeddings, we generalize and expand some results to the general setting of vector symbolic architectures (VSA) and hyperdimensional computing (HDC). Importantly, we explore the mathematical relationship between superposition, orthogonality, and tensor product. We establish the tensor product representation as the central representation, with a suite of unique properties. These include it being the most general and expressive representation, as well as being the most compressed representation that has errorrless unbinding and detection.

📄 PDF Abstract BibTeX arXiv:2305.10572

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Graph Embeddings via Tensor Products and Approximately Orthonormal Codes

2022-08-18 · Frank Qiu

We propose a dynamic graph representation method, showcasing its rich representational capacity and establishing some of its theoretical properties. Our representation falls under the bind-and-sum approach in hyperdimens…

HyperGraphX: Graph Transductive Learning with Hyperdimensional Computing and Message Passing

2025-10-28 · Guojing Cong, Tom Potok, Hamed Poursiami, Maryam Parsa arxiv

We present a novel algorithm, \hdgc, that marries graph convolution with binding and bundling operations in hyperdimensional computing for transductive graph learning. For prediction accuracy \hdgc outperforms major and …

Graph Neural NetworkGraph Learning

A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations

2021-11-11 · Denis Kleyko, Dmitri A. Rachkovskij, Evgeny Osipov, Abbas Rahimi

This two-part comprehensive survey is devoted to a computing framework most commonly known under the names Hyperdimensional Computing and Vector Symbolic Architectures (HDC/VSA). Both names refer to a family of computati…

Electrical EngineeringSurvey

THDC: Training Hyperdimensional Computing Models with Backpropagation

2026-01-27 · Hanne Dejonghe, Sam Leroux arxiv

Hyperdimensional computing (HDC) offers lightweight learning for energy-constrained devices by encoding data into high-dimensional vectors. However, its reliance on ultra-high dimensionality and static, randomly initiali…

The Hyperdimensional Transform: a Holographic Representation of Functions

2023-10-24 · Pieter Dewulf, Michiel Stock, Bernard De Baets

Integral transforms are invaluable mathematical tools to map functions into spaces where they are easier to characterize. We introduce the hyperdimensional transform as a new kind of integral transform. It converts squar…