.png){kind=icon}
返回
GGNN: Graph-Based GPU Nearest Neighbor Search
.png){kind=icon}
OA
AI
DOI：10.1109/TBDATA.2022.3161156.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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 (Wieschollek et al., 2016), FAISS (Johnson et al., 2021), and SONG (Zhao et al., 2020) started to leverage the massive parallelism offered by GPUs, GPU-based implementations are a crucial resource for today's state-of-the-art ANN methods. While most of these methods allow for faster queries, less emphasis is devoted to accelerating the construction of the underlying index structures. In this paper, we propose a novel GPU-friendly search structure based on nearest neighbor graphs and information propagation on graphs. Our method is designed to take advantage of GPU architectures to accelerate the hierarchical construction of the index structure and for performing the query. Empirical evaluation shows that GGNN significantly surpasses the state-of-the-art CPU- and GPU-based systems in terms of build-time, accuracy and search speed.
Keyword:
Graphics processing units
Indexes
Quantization (signal)
Nearest neighbor methods
Search problems
Parallel processing
Big Data
Nearest neighbor searches
graph and tree search strategies
information retrieval
approximate search
similarity search
big data
期刊
I
IF:
5.7
论文数:
887
被引数:
3.0K
机构
引用论文
Northward oceanic heat transport in the main branch of the Norwegian Atlantic Current over the late Holocene.png)
The Holocene
The HoloceneIF0
PREAI
分享收藏Explicit Not Implicit Preferences Predict Conservation Intentions for Endangered Species and BiomesPLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏
查看更多内容