Retrieval with Multiple Query Vectors through Anomalous Pattern Detection

TL;DR

This paper introduces a novel retrieval method that uses multiple query vectors and anomalous pattern detection to improve retrieval accuracy across various datasets.

Contribution

The work proposes a new retrieval approach that considers multiple queries simultaneously and leverages anomalous pattern detection to identify relevant vectors.

Findings

Larger query sets generally improve retrieval performance.

Performance gains are most significant when increasing from 1 to 8 queries.

The method is validated on image, text, and tabular datasets.

Abstract

A classical vector retrieval problem typically considers a \emph{single} query embedding vector as input and retrieves the most similar embedding vectors from a vector database. However, complex reasoning and retrieval tasks frequently require \emph{multiple query vectors}, rather than a single one. In this work, we propose a retrieval method that considers multiple query vectors simultaneously and retrieves the most relevant vectors from the database using concepts from anomalous pattern detection. Specifically, our approach leverages a set of query vectors $Q$ (with $|Q|\geq 1$), and identifies the subset of vector dimensions within $Q$ that standout (anomalous) from the rest of dimensions. Next, we scan the vector database to retrieve the set of vectors that are also anomalous across the previously identified vector dimensions and return them as our retrieved set of vectors. We validate our approach on two image datasets, a text dataset, and a tabular dataset. Overall, we observe that, across most datasets, larger query sets lead to improved retrieval performance. The improvement is most pronounced when increasing the query sets from 1 to 8, while the gains become smaller beyond that.