Scaling Approximate Nearest Neighbor Search (ANNS) to billions of vectors requires distributed indexes that balance accuracy, latency, and throughput. Yet existing index designs struggle with this tradeoff. This paper presents SPIRE, a scalable vector index based on two design decisions. First, it identifies a balanced partition granularity that avoids read-cost explosion. Second, it introduces an accuracy-preserving recursive construction that builds a multi-level index with predictable search cost and stable accuracy. In experiments with up to 8 billion vectors across 46 nodes, SPIRE achieves high scalability and up to 9.64X higher throughput than state-of-the-art systems.
@article{arxiv.2512.17264,
title = {Scalable Distributed Vector Search via Accuracy Preserving Index Construction},
author = {Yuming Xu and Qianxi Zhang and Qi Chen and Baotong Lu and Menghao Li and Philip Adams and Mingqin Li and Zengzhong Li and Jing Liu and Cheng Li and Fan Yang},
journal= {arXiv preprint arXiv:2512.17264},
year = {2025}
}