SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search
Summary: SymphonyQG tightly couples quantization and graph indices for ANN, avoids re-ranking, and aligns the graph with FastScan’s batch distances. It achieves time-accuracy at 95% recall, with 1.5-4.5x QPS gains over baselines and ≥8x faster indexing than NGT-QG. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yutong Gou (Nanyang Technological University)
- 2. Jianyang Gao (Nanyang Technological University)
- 3. Yuexuan Xu (Nanyang Technological University)
- 4. Cheng Long (Nanyang Technological University)
BibTeX Citation
@inproceedings{gou_sigmod25,
title = {{SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search}},
author = {Gou, Yutong and Gao, Jianyang and Xu, Yuexuan and Long, Cheng},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3709730},
url = {https://dl.acm.org/doi/10.1145/3709730},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 16 of 16 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 22 of 22 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next