paper-with-me

Papers

Large-Scale Approximate k-NN Graph Construction on GPU

2021-03-29 · Hui Wang, Wan-Lei Zhao, Xiangxiang Zeng

k-nearest neighbor graph is a key data structure in many disciplines such as manifold learning, machine learning and information retrieval, etc. NN-Descent was proposed as an effective solution for the graph construction problem. However, it cannot be directly transplanted to GPU due to the intensive memory accesses required in the approach. In this paper, NN-Descent has been redesigned to adapt to the GPU architecture. In particular, the number of memory accesses has been reduced significantly. The redesign fully exploits the parallelism of the GPU hardware. In the meantime, the genericness as well as the simplicity of NN-Descent are well-preserved. In addition, a simple but effective k-NN graph merge approach is presented. It allows two graphs to be merged efficiently on GPUs. More importantly, it makes the construction of high-quality k-NN graphs for out-of-GPU-memory datasets tractable. The results show that our approach is 100-250x faster than single-thread NN-Descent and is 2.5-5x faster than existing GPU-based approaches.

📄 PDF Abstract BibTeX arXiv:2103.15386

Code (1)

RayWang96/GPU_KNNG 공식 구현

Tasks

GPUgraph constructionInformation RetrievalRetrieval

Methods 이 논문이 사용한 방법론

k-NN $k$-Nearest Neighbors is a clustering-based algorithm for classification and regression. It is a a type of instance-based learning as it does not attempt to construct a…

Similar Papers 제목 키워드 기반

Fast Large-Scale Approximate Graph Construction for NLP

2012-07-01 · EMNLP 2012 7 · Amit Goyal, Hal Daum{\'e} III, Raul Guerra
graph construction

Scalable $k$-NN graph construction

2013-07-30 · Jingdong Wang, Jing Wang, Gang Zeng, Zhuowen Tu 외

The $k$-NN graph has played a central role in increasingly popular data-driven techniques for various learning and vision tasks; yet, finding an efficient and effective way to construct $k$-NN graphs remains a challenge,…

graph construction

Approximate k-NN Graph Construction: a Generic Online Approach

2018-04-09 · Wan-Lei Zhao, Hui Wang, Chong-Wah Ngo

Nearest neighbor search and k-nearest neighbor graph construction are two fundamental issues arise from many disciplines such as multimedia information retrieval, data-mining and machine learning. They become more and mo…

graph constructionInformation RetrievalRetrieval

Scalable Overload-Aware Graph-Based Index Construction for 10-Billion-Scale Vector Similarity Search

2025-02-28 · Yang Shi, Yiping Sun, Jiaolong Du, Xiaocheng Zhong 외

Approximate Nearest Neighbor Search (ANNS) is essential for modern data-driven applications that require efficient retrieval of top-k results from massive vector databases. Although existing graph-based ANNS algorithms a…

Scheduling

Relative NN-Descent: A Fast Index Construction for Graph-Based Approximate Nearest Neighbor Search

2023-10-31 · Naoki Ono, Yusuke Matsui

Approximate Nearest Neighbor Search (ANNS) is the task of finding the database vector that is closest to a given query vector. Graph-based ANNS is the family of methods with the best balance of accuracy and speed for mil…

graph construction