DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries

Jiahao Lou, Quan Yu, Shufeng Gong, Song Yu, Yanfeng Zhang, Ge Yu

Abstract: On-disk graph-based indexes are widely used in approximate nearest neighbor (ANN) search systems for large-scale, high-dimensional vectors. However, traditional coupled storage methods, which store vectors within the index, are inefficient for index updates. Coupled storage incurs excessive redundant vector reads and writes when updating the graph topology, leading to significant invalid I/O. To address this issue, we propose a decoupled storage architecture. Experimental results show that the decoupled architecture improves update speed by 10.05x for insertions and 6.89x for deletions, while the three-stage query and incremental reordering enhance query efficiency by 2.66x compared to the traditional coupled architecture.

External IDs:dblp:journals/corr/abs-2510-25401