Graph-based Approximate NN Search: A Revisit

TL;DR

This paper revisits graph-based approximate nearest neighbor search, introducing a two-stage diversification scheme for graph construction and optimized search procedures for small and large batch queries, significantly improving performance.

Contribution

It proposes a novel two-stage diversification scheme for graph construction and tailored search algorithms for different batch sizes, enhancing efficiency and accuracy in NN search.

Findings

Outperforms state-of-the-art methods on CPU and GPU

Effective trade-off between efficiency and reachability

Dynamic neighborhood visitation improves search performance

Abstract

Nearest neighbor search plays a fundamental role in many disciplines such as multimedia information retrieval, data-mining, and machine learning. The graph-based search approaches show superior performance over other types of approaches in recent studies. In this paper, the graph-based NN search is revisited. We optimize two key components in the approach, namely the search procedure and the graph that supports the search. For the graph construction, a two-stage graph diversification scheme is proposed, which makes a good trade-off between the efficiency and reachability for the search procedure that builds upon it. Moreover, the proposed diversification scheme allows the search procedure to decide dynamically how many nodes should be visited in one node's neighborhood. By this way, the computing power of the devices is fully utilized when the search is carried out under different circumstances. Furthermore, two NN search procedures are designed respectively for small and large batch queries on the GPU. The optimized NN search, when being supported by the two-stage diversified graph, outperforms all the state-of-the-art approaches on both the CPU and the GPU across all the considered large-scale datasets.