Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study

TL;DR

This paper provides a comprehensive analysis and comparison of recent Filtering Approximate Nearest Neighbor algorithms, offering a unified framework, extensive experiments, and practical guidelines for their application in high-dimensional data retrieval.

Contribution

It introduces a unified interface, taxonomy, and extensive experimental evaluation of Filtering ANN algorithms, highlighting their design tradeoffs and practical performance insights.

Findings

Different algorithms exhibit varying tradeoffs in pruning and filtering costs.

Performance varies significantly across datasets and attribute types.

Guidelines are provided for selecting suitable Filtering ANN methods.

Abstract

With the growing integration of structured and unstructured data, new methods have emerged for performing similarity searches on vectors while honoring structured attribute constraints, i.e., a process known as Filtering Approximate Nearest Neighbor (Filtering ANN) search. Since many of these algorithms have only appeared in recent years and are designed to work with a variety of base indexing methods and filtering strategies, there is a pressing need for a unified analysis that identifies their core techniques and enables meaningful comparisons. In this work, we present a unified Filtering ANN search interface that encompasses the latest algorithms and evaluate them extensively from multiple perspectives. First, we propose a comprehensive taxonomy of existing Filtering ANN algorithms based on attribute types and filtering strategies. Next, we analyze their key components, i.e., index structures, pruning strategies, and entry point selection, to elucidate design differences and tradeoffs. We then conduct a broad experimental evaluation on 10 algorithms and 12 methods across 4 datasets (each with up to 10 million items), incorporating both synthetic and real attributes and covering selectivity levels from 0.1% to 100%. Finally, an in-depth component analysis reveals the influence of pruning, entry point selection, and edge filtering costs on overall performance. Based on our findings, we summarize the strengths and limitations of each approach, provide practical guidelines for selecting appropriate methods, and suggest promising directions for future research. Our code is available at: https://github.com/lmccccc/FANNBench.