ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search

2026-07-20

AI Summary

Existing approximate nearest neighbor search (ANNS) systems struggle to simultaneously achieve high performance, functional flexibility, and low development complexity. This work proposes ANNLib, the first modular framework that decouples and independently optimizes the core algorithms and data structures underlying graph-based ANNS methods. By providing a unified interface for freely composing components, ANNLib integrates state-of-the-art algorithms alongside novel designs to efficiently support advanced functionalities such as filtered search, fully dynamic updates, and snapshot-based historical queries. Experimental results demonstrate that ANNLib matches or exceeds the performance of existing systems across diverse applications while significantly lowering the barrier to developing and deploying customized ANNS solutions.

Abstract

Approximate Nearest Neighbor Search (ANNS) plays a pivotal role in modern deep learning pipelines. Recently, many ANNS systems have been proposed to either provide broad functionality or reach high performance. However, it is yet difficult to achieve both with minimal programming efforts. We propose ANNLib to address the gap. ANNLib is a library that provides a programming framework for achieving high performance and flexible functionality in ANNS systems, based on popular graph-based ANNS algorithms. We carefully decouple and independently optimize both the algorithm and the data structure components of an ANNS system. In addition, we integrate state-of-the-art algorithms and data structures into ANNLib as modules, along with our new designs. Users can choose combinations of components to implement sophisticated settings with high performance, such as filter search, fully dynamic updates, and historical queries on snapshots. Our experiments show that our new solution provides a simple interface for various applications and achieves comparable or even better performance than previous work, specifically for each application.

Problem

• Approximate Nearest Neighbor Search
• ANNS systems
• performance
• functionality
• programming effort

Innovation

• Approximate Nearest Neighbor Search
• Modular Framework
• Algorithm-Data Structure Decoupling
• Graph-based ANNS
• Dynamic Updates