Computing the Hit Rate of Similarity Caching

TL;DR

This paper introduces the first algorithm to accurately compute the hit rate of similarity caching policies, extending TTL approximation methods to this context and validated on synthetic and real data.

Contribution

It presents a novel algorithm for calculating hit rates in similarity caching, bridging a gap in analytical tools for these policies.

Findings

Algorithm effectively computes hit rates for similarity caching policies.

Extension of TTL approximation to similarity caching is successful.

Validated on both synthetic and real-world data sets.

Abstract

Similarity caching allows requests for an item \(i\) to be served by a similar item \(i'\). Applications include recommendation systems, multimedia retrieval, and machine learning. Recently, many similarity caching policies have been proposed, but still we do not know how to compute the hit rate even for the simplest policies, like SIM-LRU and RND-LRU that are straightforward modifications of classical caching algorithms. This paper proposes the first algorithm to compute the hit rate of similarity caching policies under the independent reference model for the request process. In particular, our work shows how to extend the popular TTL approximation from classic caching to similarity caching. The algorithm is evaluated on both synthetic and real world traces.