Recursive Binding for Similarity-Preserving Hypervector Representations of Sequences

TL;DR

This paper introduces a recursive binding method for hypervector representations of sequences in hyperdimensional computing, preserving element similarity and shift equivariance, with experimental validation on symbolic strings.

Contribution

It proposes a novel recursive binding approach for sequence representations that maintain similarity and shift properties, adaptable to various HDC/VSA models.

Findings

Performance comparable to advanced existing methods

Preserves element similarity in sequence representations

Ensures shift equivariance in hypervector encoding

Abstract

Hyperdimensional computing (HDC), also known as vector symbolic architectures (VSA), is a computing framework used within artificial intelligence and cognitive computing that operates with distributed vector representations of large fixed dimensionality. A critical step for designing the HDC/VSA solutions is to obtain such representations from the input data. Here, we focus on sequences and propose their transformation to distributed representations that both preserve the similarity of identical sequence elements at nearby positions and are equivariant to the sequence shift. These properties are enabled by forming representations of sequence positions using recursive binding and superposition operations. The proposed transformation was experimentally investigated with symbolic strings used for modeling human perception of word similarity. The obtained results are on a par with more sophisticated approaches from the literature. The proposed transformation was designed for the HDC/VSA model known as Fourier Holographic Reduced Representations. However, it can be adapted to some other HDC/VSA models.