Approximate nearest neighbor search (ANNS) is a crucial problem in information retrieval and AI applications. Recently, there has been a surge of interest in graph-based ANNS algorithms due to their superior efficiency and accuracy. However, the repeated computation of distances in high-dimensional spaces constitutes the primary time cost of graph-based methods. To accelerate the search, we propose a novel routing strategy named CRouting, which bypasses unnecessary distance computations by exploiting the angle distributions of high-dimensional vectors. CRouting is designed as a plugin to optimize existing graph-based search with minimal code modifications. Our experiments show that CRouting reduces the number of distance computations by up to 41.5% and boosts queries per second by up to 1.48× on two predominant graph indexes, HNSW and NSG. Code is publicly available at https://github.com/ISCS-ZJU/CRouting.
@article{arxiv.2509.00365,
title = {CRouting: Reducing Expensive Distance Calls in Graph-Based Approximate Nearest Neighbor Search},
author = {Zhenxin Li and Shuibing He and Jiahao Guo and Xuechen Zhang and Xian-He Sun and Gang Chen},
journal= {arXiv preprint arXiv:2509.00365},
year = {2025}
}