Distribution-Aware Exploration for Adaptive HNSW Search
Summary: Query-adaptive HNSW exploration factor (Ada-ef) for ANNS: statistically model query–data similarity to set per-query ef under a declarative target recall. Distribution-aware, update-friendly, avoids over/under-searching; 4x latency, 50x compute, 100x memory gains.
(summarized by gpt-5.4-mini on Apr 11 2026)
@inproceedings{zhang_sigmod26,
title = {{Distribution-Aware Exploration for Adaptive HNSW Search}},
author = {Zhang, Chao and Miller, Renée J.},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786639},
url = {https://dl.acm.org/doi/10.1145/3786639},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
Rank
Citing Paper
Year
Venue
Pagerank
PreviousPage 1 / 1Next
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.