CleANN: Efficient Full Dynamism in Graph-based Approximate Nearest Neighbor Search

TL;DR

CleANN is a novel graph-based approximate nearest neighbor search system that efficiently supports full dynamism, including updates and searches, while maintaining high query quality and significantly improving throughput on large datasets.

Contribution

The paper introduces CleANN, the first concurrent ANNS index that effectively handles full dynamism with high efficiency and maintained quality, addressing limitations of previous static and dynamic methods.

Findings

Achieves 7-1200x throughput improvement on large datasets.

Maintains query quality comparable to static indexes.

Operates efficiently with concurrent updates and searches.

Abstract

Approximate nearest neighbor search (ANNS) has become a quintessential algorithmic problem for various other foundational data tasks for AI workloads. Graph-based ANNS indexes have superb empirical trade-offs in indexing cost, query efficiency, and query approximation quality. Most existing graph-based indexes are designed for the static scenario, where there are no updates to the data after the index is constructed. However, full dynamism (insertions, deletions, and searches) is crucial to providing up-to-date responses in applications using vector databases. It is desirable that the index efficiently supports updates and search queries concurrently. Existing dynamic graph-based indexes suffer from at least one of the following problems: (1) the query quality degrades as updates happen; and (2) the graph structure updates used to maintain the index quality upon updates are global and thus expensive. To solve these problems, we propose the CleANN system which consists of three main components: (1) workload-aware linking of diverse search tree descendants to combat distribution shift; (2)query-adaptive on-the-fly neighborhood consolidation to efficiently handle deleted nodes; and (3) semi-lazy memory cleaning to clean up stale information in the data structure and reduce the work spent by the first two components. We evaluate CleANN on 7 diverse datasets on fully dynamic workloads and find that CleANN has query quality at least as good as if the index had been built statically using the corresponding data. In the in-memory setting using 56 hyper-threads, with all types of queries running concurrently, at the same recall level, CleANN achieves 7-1200x throughput improvement on million-scale real-world datasets. To the best of our knowledge, CleANN is the first concurrent ANNS index to achieve such efficiency while maintaining quality under full dynamism.