Hierarchical Clustering-Based Graphs for Large Scale Approximate Nearest Neighbor Search

作者：

Highlights：

• Nearest Neighbors (NN) search based on NN-graphs outperforms classical approaches.

• Clustering results are used for creating efficient NN-graphs.

• Guided navigation on NN-graphs improves significantly the effectiveness results.

• Non-randomized initial vertex selection improves search results at high speedups.

摘要

•Nearest Neighbors (NN) search based on NN-graphs outperforms classical approaches.•Clustering results are used for creating efficient NN-graphs.•Guided navigation on NN-graphs improves significantly the effectiveness results.•Non-randomized initial vertex selection improves search results at high speedups.

论文关键词：Approximate nearest neighbors search,Graph-based search,Hierarchical clustering,Guided search

论文评审过程：Received 28 August 2018, Revised 20 March 2019, Accepted 15 July 2019, Available online 15 July 2019, Version of Record 26 July 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.106970