DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries

TL;DR

DESSERT is a new approximate algorithm for vector set search that significantly speeds up semantic search tasks with minimal impact on recall, demonstrated within ColBERT on benchmark datasets.

Contribution

We introduce DESSERT, an efficient approximate search algorithm for vector set queries with strong theoretical guarantees and practical performance improvements.

Findings

2-5x speedup in retrieval benchmarks

Minimal loss in recall with DESSERT integration

Effective for semantic search applications

Abstract

We study the problem of $\textit{vector set search}$ with $\textit{vector set queries}$. This task is analogous to traditional near-neighbor search, with the exception that both the query and each element in the collection are $\textit{sets}$ of vectors. We identify this problem as a core subroutine for semantic search applications and find that existing solutions are unacceptably slow. Towards this end, we present a new approximate search algorithm, DESSERT (${\bf D}$ESSERT ${\bf E}$ffeciently ${\bf S}$earches ${\bf S}$ets of ${\bf E}$mbeddings via ${\bf R}$etrieval ${\bf T}$ables). DESSERT is a general tool with strong theoretical guarantees and excellent empirical performance. When we integrate DESSERT into ColBERT, a state-of-the-art semantic search model, we find a 2-5x speedup on the MS MARCO and LoTTE retrieval benchmarks with minimal loss in recall, underscoring the effectiveness and practical applicability of our proposal.