Scalable Graph Indexing using GPUs for Approximate Nearest Neighbor Search
Summary: Tagore: GPU library for fast construction of refinement-based graph ANNS (NSG/Vamana), with GNN-Descent — a two-phase parallel GPU k-NN initializer — and CFS, a universal pruning formulation implemented via two GPU kernels. Also an async GPU–CPU–disk indexing engine with cluster-aware caching for out-of-core data, yielding 1.32–112.79× speedups while preserving index quality. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zhonggen Li (Zhejiang University)
- 2. Xiangyu Ke (Zhejiang University)
- 3. Yifan Zhu (Zhejiang University)
- 4. Bocheng Yu (Zhejiang University)
- 5. Baihua Zheng (Singapore Management University)
- 6. Yunjun Gao (Zhejiang University)
BibTeX Citation
@inproceedings{li_sigmod26,
title = {{Scalable Graph Indexing using GPUs for Approximate Nearest Neighbor Search}},
author = {Li, Zhonggen and Ke, Xiangyu and Zhu, Yifan and Yu, Bocheng and Zheng, Baihua and Gao, Yunjun},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769825},
url = {https://dl.acm.org/doi/10.1145/3769825},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,846 | HEXA: A Disjoint-Subgraph-Based Indexing Framework for Approximate Nearest Neighbor Search at Billion Scale | 2026 | VLDB | 4.9769913e-05 |
| 10,882 | GPU-Native Approximate Nearest Neighbor Search with IVF-RaBitQ: Fast Index Build and Search | 2026 | VLDB | 4.9769913e-05 |
| 11,037 | Advances of Query Processing in Vector Databases | 2026 | VLDB | 4.9769913e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 30 of 30 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next