LANNS: A Web-Scale Approximate Nearest Neighbor Lookup System

by   Ishita Doshi, et al.

Nearest neighbor search (NNS) has a wide range of applications in information retrieval, computer vision, machine learning, databases, and other areas. Existing state-of-the-art algorithm for nearest neighbor search, Hierarchical Navigable Small World Networks(HNSW), is unable to scale to large datasets of 100M records in high dimensions. In this paper, we propose LANNS, an end-to-end platform for Approximate Nearest Neighbor Search, which scales for web-scale datasets. Library for Large Scale Approximate Nearest Neighbor Search (LANNS) is deployed in multiple production systems for identifying topK (100 ≤ topK ≤ 200) approximate nearest neighbors with a latency of a few milliseconds per query, high throughput of 2.5k Queries Per Second (QPS) on a single node, on large (∼180M data points) high dimensional (50-2048 dimensional) datasets.


page 1

page 2

page 3

page 4


Approximate Nearest Neighbor Search in High Dimensions

The nearest neighbor problem is defined as follows: Given a set P of n p...

Subspace Approximation for Approximate Nearest Neighbor Search in NLP

Most natural language processing tasks can be formulated as the approxim...

The Role of Local Intrinsic Dimensionality in Benchmarking Nearest Neighbor Search

This paper reconsiders common benchmarking approaches to nearest neighbo...

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...

scikit-hubness: Hubness Reduction and Approximate Neighbor Search

This paper introduces scikit-hubness, a Python package for efficient nea...

KNN-DBSCAN: a DBSCAN in high dimensions

Clustering is a fundamental task in machine learning. One of the most su...

Optimized Cartesian K-Means

Product quantization-based approaches are effective to encode high-dimen...