FINGER: Fast Inference for Graph-based Approximate Nearest Neighbor Search

06/22/2022
by   Patrick H. Chen, et al.
21

Approximate K-Nearest Neighbor Search (AKNNS) has now become ubiquitous in modern applications, for example, as a fast search procedure with two tower deep learning models. Graph-based methods for AKNNS in particular have received great attention due to their superior performance. These methods rely on greedy graph search to traverse the data points as embedding vectors in a database. Under this greedy search scheme, we make a key observation: many distance computations do not influence search updates so these computations can be approximated without hurting performance. As a result, we propose FINGER, a fast inference method to achieve efficient graph search. FINGER approximates the distance function by estimating angles between neighboring residual vectors with low-rank bases and distribution matching. The approximated distance can be used to bypass unnecessary computations, which leads to faster searches. Empirically, accelerating a popular graph-based method named HNSW by FINGER is shown to outperform existing graph-based methods by 20 benchmark datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/03/2019

Graph based Nearest Neighbor Search: Promises and Failures

Recently, graph based nearest neighbor search gets more and more popular...
research
07/01/2019

Graph-based Nearest Neighbor Search: From Practice to Theory

Graph-based approaches are empirically shown to be very successful for a...
research
04/03/2019

A Comparative Study on Hierarchical Navigable Small World Graphs

Hierarchical navigable small world (HNSW) graphs get more and more popul...
research
09/01/2023

General and Practical Tuning Method for Off-the-Shelf Graph-Based Index: SISAP Indexing Challenge Report by Team UTokyo

Despite the efficacy of graph-based algorithms for Approximate Nearest N...
research
07/22/2022

Graph-Based Tests for Multivariate Covariate Balance Under Multi-Valued Treatments

We propose the use of non-parametric, graph-based tests to assess the di...
research
05/07/2023

Scaling Graph-Based ANNS Algorithms to Billion-Size Datasets: A Comparative Analysis

Algorithms for approximate nearest-neighbor search (ANNS) have been the ...
research
04/07/2023

Similarity search in the blink of an eye with compressed indices

Nowadays, data is represented by vectors. Retrieving those vectors, amon...

Please sign up or login with your details

Forgot password? Click here to reset