Key-value memory in the brain

TL;DR

This paper reviews key-value memory systems, highlighting their ability to optimize storage fidelity and retrieval discriminability, and explores their computational foundations, applications, and potential biological implementations.

Contribution

It provides a comprehensive overview of key-value memory models, connecting their theoretical basis with practical applications and biological plausibility.

Findings

Key-value memory systems improve memory retrieval accuracy.

They are widely used in modern machine learning models.

Potential biological implementations are discussed.

Abstract

Classical models of memory in psychology and neuroscience rely on similarity-based retrieval of stored patterns, where similarity is a function of retrieval cues and the stored patterns. While parsimonious, these models do not allow distinct representations for storage and retrieval, despite their distinct computational demands. Key-value memory systems, in contrast, distinguish representations used for storage (values) and those used for retrieval (keys). This allows key-value memory systems to optimize simultaneously for fidelity in storage and discriminability in retrieval. We review the computational foundations of key-value memory, its role in modern machine learning systems, related ideas from psychology and neuroscience, applications to a number of empirical puzzles, and possible biological implementations.