Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search

05/08/2022
by   Harsha Vardhan Simhadri, et al.
0

Despite the broad range of algorithms for Approximate Nearest Neighbor Search, most empirical evaluations of algorithms have focused on smaller datasets, typically of 1 million points <cit.>. However, deploying recent advances in embedding based techniques for search, recommendation and ranking at scale require ANNS indices at billion, trillion or larger scale. Barring a few recent papers, there is limited consensus on which algorithms are effective at this scale vis-à-vis their hardware cost. This competition compares ANNS algorithms at billion-scale by hardware cost, accuracy and performance. We set up an open source evaluation framework and leaderboards for both standardized and specialized hardware. The competition involves three tracks. The standard hardware track T1 evaluates algorithms on an Azure VM with limited DRAM, often the bottleneck in serving billion-scale indices, where the embedding data can be hundreds of GigaBytes in size. It uses FAISS <cit.> as the baseline. The standard hardware track T2 additional allows inexpensive SSDs in addition to the limited DRAM and uses DiskANN <cit.> as the baseline. The specialized hardware track T3 allows any hardware configuration, and again uses FAISS as the baseline. We compiled six diverse billion-scale datasets, four newly released for this competition, that span a variety of modalities, data types, dimensions, deep learning models, distance functions and sources. The outcome of the competition was ranked leaderboards of algorithms in each track based on recall at a query throughput threshold. Additionally, for track T3, separate leaderboards were created based on recall as well as cost-normalized and power-normalized query throughput.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/09/2018

Learning to Index for Nearest Neighbor Search

In this study, we present a novel ranking model based on learning the ne...
research
08/29/2023

CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs

Approximate Nearest Neighbor Search (ANNS) plays a critical role in vari...
research
01/04/2023

Automating Nearest Neighbor Search Configuration with Constrained Optimization

The approximate nearest neighbor (ANN) search problem is fundamental to ...
research
03/20/2017

Fast Spectral Ranking for Similarity Search

Despite the success of deep learning on representing images for particul...
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
07/12/2022

Accelerating Large-Scale Graph-based Nearest Neighbor Search on a Computational Storage Platform

K-nearest neighbor search is one of the fundamental tasks in various app...

Please sign up or login with your details

Forgot password? Click here to reset