Developing a Foundation of Vector Symbolic Architectures Using Category Theory

TL;DR

This paper applies category theory to Vector Symbolic Architectures (VSAs), providing a formal framework that unifies and extends current models, potentially leading to new designs and better understanding of their compositionality.

Contribution

It introduces a novel category-theoretic formalization of VSAs, generalizing from vectors to co-presheaves and describing VSA operations as right Kan extensions.

Findings

Formalization connects VSA operations to category theory concepts.

Worked examples demonstrate the applicability of the formalization.

Suggests new VSA designs based on the categorical framework.

Abstract

Connectionist approaches to machine learning, \emph{i.e.} neural networks, are enjoying a considerable vogue right now. However, these methods require large volumes of data and produce models that are uninterpretable to humans. An alternative framework that is compatible with neural networks and gradient-based learning, but explicitly models compositionality, is Vector Symbolic Architectures (VSAs). VSAs are a family of algebras on high-dimensional vector representations. They arose in cognitive science from the need to unify neural processing and the kind of symbolic reasoning that humans perform. While machine learning methods have benefited from category-theoretical analyses, VSAs have not yet received similar treatment. In this paper, we present a first attempt at applying category theory to VSAs. Specifically, We generalise from vectors to co-presheaves, and describe VSA operations as the right Kan extensions of the external tensor product. This formalisation involves a proof that the right Kan extension in such cases can be expressed as simple, element-wise operations. We validate our formalisation with worked examples that connect to current VSA implementations, while suggesting new possible designs for VSAs.