Graph Reordering for Cache-Efficient Near Neighbor Search

04/07/2021
by   Benjamin Coleman, et al.
0

Graph search is one of the most successful algorithmic trends in near neighbor search. Several of the most popular and empirically successful algorithms are, at their core, a simple walk along a pruned near neighbor graph. Such algorithms consistently perform at the top of industrial speed benchmarks for applications such as embedding search. However, graph traversal applications often suffer from poor memory access patterns, and near neighbor search is no exception to this rule. Our measurements show that popular search indices such as the hierarchical navigable small-world graph (HNSW) can have poor cache miss performance. To address this problem, we apply graph reordering algorithms to near neighbor graphs. Graph reordering is a memory layout optimization that groups commonly-accessed nodes together in memory. We present exhaustive experiments applying several reordering algorithms to a leading graph-based near neighbor method based on the HNSW index. We find that reordering improves the query time by up to 40 time needed to reorder the graph is negligible compared to the time required to construct the index.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/10/2023

A Theoretical Analysis Of Nearest Neighbor Search On Approximate Near Neighbor Graph

Graph-based algorithms have demonstrated state-of-the-art performance in...
research
05/20/2021

FreshDiskANN: A Fast and Accurate Graph-Based ANN Index for Streaming Similarity Search

Approximate nearest neighbor search (ANNS) is a fundamental building blo...
research
06/22/2021

Practical Near Neighbor Search via Group Testing

We present a new algorithm for the approximate near neighbor problem tha...
research
11/16/2021

Mathematical Models for Local Sensing Hashes

As data volumes continue to grow, searches in data are becoming increasi...
research
02/18/2019

RACE: Sub-Linear Memory Sketches for Approximate Near-Neighbor Search on Streaming Data

We demonstrate the first possibility of a sub-linear memory sketch for s...
research
08/29/2023

CAPS: A Practical Partition Index for Filtered Similarity Search

With the surging popularity of approximate near-neighbor search (ANNS), ...
research
06/13/2023

Practice with Graph-based ANN Algorithms on Sparse Data: Chi-square Two-tower model, HNSW, Sign Cauchy Projections

Sparse data are common. The traditional “handcrafted” features are often...

Please sign up or login with your details

Forgot password? Click here to reset