2025/10/03 by Xiang Li, Qiong Chang, Li, Xiang +5
Computer Science · #Advanced Image and Video Retrieval Techniques #Data Management and Algorithms #Distributed #FOS: Computer and information sciences #Graph Theory and Algorithms #Parallel #and Cluster Computing (cs.DC)
paper · pdf · doi:10.48550/arxiv.2510.02774
openalex publication_date 2025/10/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Relative Nearest Neighbor Descent (RNN-Descent) is a state-of-the-art algorithm for constructing sparse approximate nearest neighbor (ANN) graphs by combining the iterative refinement of NN-Descent with the edge-pruning rules of the Relative Neighborhood Graph (RNG). It has demonstrated strong effectiveness in large-scale search tasks such as information retrieval and related tasks. However, as the amount and dimensionality of data increase, the complexity of graph construction in RNN-Descent rises sharply, making this stage increasingly time-consuming and even prohibitive for subsequent query processing. In this paper, we propose GRNND, the first GPU-parallel algorithm of RNN-Descent designed to fully exploit GPU architecture. GRNND introduces a disordered neighbor propagation strategy to mitigate synchronized update traps, enhancing structural diversity, and avoiding premature convergence during parallel execution. It also leverages warp-level cooperative operations and a double-buffered neighbor pool with fixed capacity for efficient memory access, eliminate contention, and enable highly parallelized neighbor updates. Extensive experiments demonstrate that GRNND consistently outperforms existing CPU- and GPU-based methods. GRNND achieves 2.4 to 51.7x speedup over existing GPU methods, and 17.8 to 49.8x speedup over CPU methods.