English
Related papers

Related papers: HDIdx: High-Dimensional Indexing for Efficient App…

200 papers

This work addresses the problem of billion-scale nearest neighbor search. The state-of-the-art retrieval systems for billion-scale databases are currently based on the inverted multi-index, the recently proposed generalization of the…

Computer Vision and Pattern Recognition · Computer Science 2018-07-24 Dmitry Baranchuk , Artem Babenko , Yury Malkov

We propose Partition Dimensions Across (PDX), a data layout for vectors (e.g., embeddings) that, similar to PAX [6], stores multiple vectors in one block, using a vertical layout for the dimensions (Figure 1). PDX accelerates exact and…

Databases · Computer Science 2025-03-07 Leonardo Kuffo , Elena Krippner , Peter Boncz

Bregman distances (also known as Bregman divergences) are widely used in machine learning, speech recognition and signal processing, and kNN searches with Bregman distances have become increasingly important with the rapid advances of…

Databases · Computer Science 2020-06-02 Yang Song , Yu Gu , Rui Zhang , Ge Yu

Software-based approaches for search over encrypted data are still either challenged by lack of proper, low-leakage encryption or slow performance. Existing hardware-based approaches do not scale well due to hardware limitations and…

Cryptography and Security · Computer Science 2017-03-16 Benny Fuhry , Raad Bahmani , Ferdinand Brasser , Florian Hahn , Florian Kerschbaum , Ahmad-Reza Sadeghi

Nearest-neighbor query processing is a fundamental operation for many image retrieval applications. Often, images are stored and represented by high-dimensional vectors that are generated by feature-extraction algorithms. Since tree-based…

Databases · Computer Science 2019-12-17 Omid Jafari , Khandker Mushfiqul Islam , Parth Nagarkar

The fastest indexes for Approximate Nearest Neighbor Search today are also the slowest to build: graph-based methods like HNSW and Vamana achieve state-of-the-art query performance but have large construction times due to relying on…

Databases · Computer Science 2026-05-26 Tobias Rubel , Richard Wen , Laxman Dhulipala , Lars Gottesbüren , Rajesh Jayaram , Jakub Łącki

This paper introduces scikit-hubness, a Python package for efficient nearest neighbor search in high-dimensional spaces. Hubness is an aspect of the curse of dimensionality, and is known to impair various learning tasks, including…

Machine Learning · Computer Science 2021-01-12 Roman Feldbauer , Thomas Rattei , Arthur Flexer

Similarity search is a fundamental algorithmic primitive, widely used in many computer science disciplines. Given a set of points $S$ and a radius parameter $r>0$, the $r$-near neighbor ($r$-NN) problem asks for a data structure that, given…

Data Structures and Algorithms · Computer Science 2021-01-27 Martin Aumüller , Sariel Har-Peled , Sepideh Mahabadi , Rasmus Pagh , Francesco Silvestri

We consider the problem of finding high dimensional approximate nearest neighbors. Suppose there are d independent rare features, each having its own independent statistics. A point x will have x_{i}=0 denote the absence of feature i, and…

Information Theory · Computer Science 2008-10-24 Moshe Dubiner

The in-memory algorithms for approximate nearest neighbor search (ANNS) have achieved great success for fast high-recall search, but are extremely expensive when handling very large scale database. Thus, there is an increasing request for…

Databases · Computer Science 2021-11-17 Qi Chen , Bing Zhao , Haidong Wang , Mingqin Li , Chuanjie Liu , Zengzhong Li , Mao Yang , Jingdong Wang

Approximate $k$ nearest neighbor (AKNN) search in high-dimensional space is a foundational problem in vector databases with widespread applications. Among the numerous AKNN indexes, Proximity Graph-based indexes achieve state-of-the-art…

Databases · Computer Science 2026-02-20 Liuchang Jing , Mingyu Yang , Lei Li , Jianbin Qin , Wei Wang

Efficient index structures for fast approximate nearest neighbor queries are required in many applications such as recommendation systems. In high-dimensional spaces, many conventional methods suffer from excessive usage of memory and slow…

Fast k-Nearest Neighbor search over real-valued vector spaces (KNN) is an important algorithmic task for information retrieval and recommendation systems. We present a method for using reduced precision to represent vectors through…

Information Retrieval · Computer Science 2021-10-19 Anthony Ko , Iman Keivanloo , Vihan Lakshman , Eric Schkufza

The explosive growth in big data has attracted much attention in designing efficient indexing and search methods recently. In many critical applications such as large-scale search and pattern matching, finding the nearest neighbors to a…

Machine Learning · Computer Science 2015-09-21 Jun Wang , Wei Liu , Sanjiv Kumar , Shih-Fu Chang

Distributed Nearest Neighbor Search (DNNS) locates service nodes that have shortest interactive delay towards requesting hosts. DNNS provides an important service for large-scale latency sensitive networked applications, such as VoIP,…

Distributed, Parallel, and Cluster Computing · Computer Science 2011-08-10 Yongquan Fu , Yijie Wang , Ernst Biersack

Similarity-preserving hashing is a widely-used method for nearest neighbour search in large-scale image retrieval tasks. There has been considerable research on generating efficient image representation via the deep-network-based hashing…

Computer Vision and Pattern Recognition · Computer Science 2017-10-20 Hanjiang Lai , Yan Pan

Traditional database management systems need help efficiently represent and querying the complex, high-dimensional data prevalent in modern applications. Vector databases offer a solution by storing data as numerical vectors within a…

Databases · Computer Science 2024-03-20 Gulshan Yadav , RahulKumar Yadav , Mansi Viramgama , Mayank Viramgama , Apeksha Mohite

Approximate nearest neighbor (ANN) search in high dimensions is an integral part of several computer vision systems and gains importance in deep learning with explicit memory representations. Since PQT, FAISS, and SONG started to leverage…

Computer Vision and Pattern Recognition · Computer Science 2022-04-08 Fabian Groh , Lukas Ruppert , Patrick Wieschollek , Hendrik P. A. Lensch

Approximate Nearest Neighbor Search (ANNS) in high dimensional space is essential in database and information retrieval. Recently, there has been a surge of interest in exploring efficient graph-based indices for the ANNS problem. Among…

Information Retrieval · Computer Science 2021-03-19 Cong Fu , Changxu Wang , Deng Cai

High-dimensional approximate $K$ nearest neighbor search (AKNN) is a fundamental task for various applications, including information retrieval. Most existing algorithms for AKNN can be decomposed into two main components, i.e., candidate…

Databases · Computer Science 2024-12-03 Liwei Deng , Penghao Chen , Ximu Zeng , Tianfu Wang , Yan Zhao , Kai Zheng