RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search
Summary: Shows cross-modal OOD queries violate conventional ANNS assumptions: they deviate spatially and have mutually distant neighbors. RoarGraph exploits query distributions via a projected bipartite graph, delivering up to 3.56× faster search at 90% recall. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Meng Chen (Fudan University)
- 2. Kai Zhang (Fudan University)
- 3. Zhenying He (Fudan University)
- 4. Yinan Jing (Fudan University)
- 5. X.Sean Wang (Fudan University)
BibTeX Citation
@article{chen_vldb24,
title = {{RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search}},
author = {Chen, Meng and Zhang, Kai and He, Zhenying and Jing, Yinan and Wang, X.Sean},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {11},
pages = {2735--2749},
doi = {10.14778/3681954.3681959},
url = {https://doi.org/10.14778/3681954.3681959},
year = {2024}
}
Incoming Citations (Sorted by Pagerank)
Showing 12 of 12 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next