RT-RkNN: Reverse k Nearest Neighbor Queries as a Graphics Ray Casting Problem

2026-05-26

AI Summary

This work addresses the significant degradation in pruning efficiency of traditional R-tree-based reverse k-nearest neighbor (RkNN) queries when the number of facilities is small, user density is high, or k is large. The authors propose a novel reformulation of the two-dimensional RkNN query as a ray casting problem from computer graphics, modeling users as rays and facilities as geometric primitives. Leveraging modern GPU hardware with dedicated ray-tracing units, the method enables highly efficient query processing. This approach overcomes the limitations of conventional spatial pruning strategies and maintains superior filtering performance even under extreme conditions, substantially outperforming state-of-the-art algorithms.

Abstract

Reverse k nearest neighbor (RkNN) queries are fundamental in spatial databases, location-based analytics, and recommendation systems. Existing state-of-the-art techniques rely on spatial pruning supported by R-trees and their variants. However, their pruning effectiveness degrades significantly in challenging scenarios where the number of facilities is small, the user population is dense, or the value of k is large. To overcome these limitations, this work reformulates the RkNN query problem in two-dimensional geometric spaces as a graphics ray-casting problem, where users are modeled as rays and facilities are represented as geometric primitives. Based on this formulation, the first algorithm and implementation exploiting dedicated hardware ray-tracing cores on modern GPUs are developed. This novel approach preserves strong filtering performance even for large values of k, dense user populations, and highly sparse facility distributions. Extensive experimental results demonstrate that the proposed method outperforms state-of-the-art algorithms across diverse settings, particularly in scenarios where traditional pruning strategies become inefficient.

Problem

• Reverse k Nearest Neighbor
• spatial pruning
• dense user population
• large k
• sparse facility distribution

Innovation

• Reverse k Nearest Neighbor
• Ray Casting
• GPU Ray Tracing
• Spatial Query
• Geometric Primitives