FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Zekai, Jin, Jiabao, Cheng, Peng, Zhong, Xiaoyao, Chen, Lei, Tong, Yongxin, Shen, Zhitao, Song, Jingkuan, Shen, Heng Tao, Lin, Xuemin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908906772496384
author Wu, Zekai
Jin, Jiabao
Cheng, Peng
Zhong, Xiaoyao
Chen, Lei
Tong, Yongxin
Shen, Zhitao
Song, Jingkuan
Shen, Heng Tao
Lin, Xuemin
author_facet Wu, Zekai
Jin, Jiabao
Cheng, Peng
Zhong, Xiaoyao
Chen, Lei
Tong, Yongxin
Shen, Zhitao
Song, Jingkuan
Shen, Heng Tao
Lin, Xuemin
contents As the state-of-the-art methods for high-dimensional data retrieval, Approximate Nearest Neighbor Search (ANNS) approaches with graph-based indexes have attracted increasing attention and play a crucial role in many real-world applications, e.g., retrieval-augmented generation (RAG) and recommendation systems. Unlike the extensive works focused on designing efficient graph-based ANNS methods, this paper delves into merging multiple existing graph-based indexes into a single one, which is also crucial in many real-world scenarios (e.g., cluster consolidation in distributed systems and read-write contention in real-time vector databases). We propose a Fast Graph-based Indexes Merging (FGIM) framework with three core techniques: (1) Proximity Graphs (PGs) to $k$ Nearest Neighbor Graph ($k$-NNG) transformation used to extract potential candidate neighbors from input graph-based indexes through cross-querying, (2) $k$-NNG refinement designed to identify overlooked high-quality neighbors and maintain graph connectivity, and (3) $k$-NNG to PG transformation aimed at improving graph navigability and enhancing search performance. Then, we integrate our FGIM framework with the state-of-the-art ANNS method, HNSW, and other existing mainstream graph-based methods to demonstrate its generality and merging efficiency. Extensive experiments on six real-world datasets show that our FGIM framework is applicable to various mainstream graph-based ANNS methods, achieves up to 3.5$\times$ speedup over HNSW's incremental construction and an average of 7.9$\times$ speedup for methods without incremental support, while maintaining comparable or superior search performance.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21710
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search
Wu, Zekai
Jin, Jiabao
Cheng, Peng
Zhong, Xiaoyao
Chen, Lei
Tong, Yongxin
Shen, Zhitao
Song, Jingkuan
Shen, Heng Tao
Lin, Xuemin
Databases
As the state-of-the-art methods for high-dimensional data retrieval, Approximate Nearest Neighbor Search (ANNS) approaches with graph-based indexes have attracted increasing attention and play a crucial role in many real-world applications, e.g., retrieval-augmented generation (RAG) and recommendation systems. Unlike the extensive works focused on designing efficient graph-based ANNS methods, this paper delves into merging multiple existing graph-based indexes into a single one, which is also crucial in many real-world scenarios (e.g., cluster consolidation in distributed systems and read-write contention in real-time vector databases). We propose a Fast Graph-based Indexes Merging (FGIM) framework with three core techniques: (1) Proximity Graphs (PGs) to $k$ Nearest Neighbor Graph ($k$-NNG) transformation used to extract potential candidate neighbors from input graph-based indexes through cross-querying, (2) $k$-NNG refinement designed to identify overlooked high-quality neighbors and maintain graph connectivity, and (3) $k$-NNG to PG transformation aimed at improving graph navigability and enhancing search performance. Then, we integrate our FGIM framework with the state-of-the-art ANNS method, HNSW, and other existing mainstream graph-based methods to demonstrate its generality and merging efficiency. Extensive experiments on six real-world datasets show that our FGIM framework is applicable to various mainstream graph-based ANNS methods, achieves up to 3.5$\times$ speedup over HNSW's incremental construction and an average of 7.9$\times$ speedup for methods without incremental support, while maintaining comparable or superior search performance.
title FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search
topic Databases
url https://arxiv.org/abs/2603.21710