GGNN: Graph-based GPU Nearest Neighbor Search

TL;DR

This paper introduces GGNN, a GPU-optimized nearest neighbor graph structure that accelerates index construction and search in high-dimensional spaces, outperforming existing CPU and GPU methods in speed and accuracy.

Contribution

The paper presents a novel GPU-friendly graph-based index structure for approximate nearest neighbor search, focusing on fast construction and high-quality search results.

Findings

GGNN significantly reduces index build time.

GGNN achieves higher search accuracy.

GGNN outperforms state-of-the-art methods in speed and accuracy.

Abstract

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 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.