We present a new approach for the approximate K-nearest neighbor search based on
navigable small world graphs with controllable hierarchy (Hierarchical NSW, HNSW). The …

The recent popularity of learned embeddings has fueled the growth of massive collections of
high-dimensional (high-d) vectors that model complex data. Finding similar vectors in these …

Pre-trained language representation models (PLMs) such as BERT and Enhanced
Representation through kNowledge IntEgration (ERNIE) have been integral to achieving …

Approximate nearest-neighbor search (ANNS) algorithms are a key part of the modern deep
learning stack due to enabling efficient similarity search over high-dimensional vector space …

We take a first step towards a rigorous asymptotic analysis of graph-based approaches for
finding (approximate) nearest neighbors in high-dimensional spaces, by analyzing the …

The expensive acquisition of labeled data limits the practical use of supervised learning on
polarimetric synthetic aperture radar (PolSAR) image analysis. Semi-supervised learning …

In this thesis we advance state-of-the-art of the non-metric k-NN search by carrying out an
extensive empirical evaluation (both and intrinsic) of generic methods for k-NN search. This …

This document covers a library for fast similarity (k-NN) search. It describes only search
methods and distances (spaces). Details about building, installing, Python bindings can be …

Indoor positioning systems consist of identifying the physical location of devices inside
buildings. They are usually based on the signal strength of a device packet received by a set …

The main goal of an Indoor Positioning System (IPS) is to estimate the position of mobile
devices in indoor environments. For this purpose, the primary source of information is the …