Through the Lens of Hubness: A Revisit on Graph-Based Approximate Nearest Neighbor Search: [Experiments & Analysis]
Summary: Shows hubness—central hubs and isolated anti-hubs—as the root of graph-ANNS tail latency and greedy-search failures. A unified taxonomy and 100M-scale experiments reveal mitigation trade-offs; hubness-aware pruning improves outlier performance cheaply. (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. Xiaoliang Xu (Hangzhou Dianzi University)
- 2. Haonan Dai (Hangzhou Dianzi University)
- 3. Can Li (Hangzhou Dianzi University)
- 4. Mengzhao Wang (Hangzhou Dianzi University)
- 5. Qiang Yue (Hangzhou Dianzi University)
BibTeX Citation
@inproceedings{xu_sigmod26,
title = {{Through the Lens of Hubness: A Revisit on Graph-Based Approximate Nearest Neighbor Search: [Experiments \& Analysis]}},
author = {Xu, Xiaoliang and Dai, Haonan and Li, Can and Wang, Mengzhao and Yue, Qiang},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802120},
url = {https://dl.acm.org/doi/10.1145/3802120},
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 25 of 25 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next