PathSeer: Adaptive Neighbor Handling for Efficient Filtered ANN Search
Summary: PathSeer accelerates filtered ANN search with a fusion index combining filter-first and distance-first neighbor handling. It dynamically adjusts their traversal mix per step and tunes it to workload characteristics, improving throughput up to 47.4× without recall loss. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhiyue Li (Tsinghua University)
- 2. Guangyan Zhang (Tsinghua University)
- 3. Ruochun Jin (National University of Defense Technology)
- 4. Bojun Li (National University of Defense Technology)
- 5. Xiaoguang Ren (Intelligent Game and Decision Lab)
- 6. Wenjing Yang (National University of Defense Technology)
BibTeX Citation
@inproceedings{li_sigmod26,
title = {{PathSeer: Adaptive Neighbor Handling for Efficient Filtered ANN Search}},
author = {Li, Zhiyue and Zhang, Guangyan and Jin, Ruochun and Li, Bojun and Ren, Xiaoguang and Yang, Wenjing},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802098},
url = {https://dl.acm.org/doi/10.1145/3802098},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 14 of 14 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next