DBScholar

Back to papers

RED-ANNS: An RDMA-Enabled Distributed Framework for Graph-Based Approximate Nearest Neighbor Search

Summary: RED-ANNS maintains a logically global ANN graph across RDMA-connected nodes, avoiding partition-induced indexing degradation. Locality-aware placement, affinity scheduling, and latency-hiding best-first search mitigate remote-access costs, yielding up to 2.5× speedups. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
14528
Venue
VLDB
Year
2026
Pagerank
5.093636e-05
Overall Rank
10,585 | 27.38%
DOI
10.14778/3778092.3778101

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{chen_vldb26,
        title = {{RED-ANNS: An RDMA-Enabled Distributed Framework for Graph-Based Approximate Nearest Neighbor Search}},
        author = {Chen, Yue and Zhang, Kai and Chen, Sipeng and Xiao, Shihai and Zou, Xiaomin and Ren, Ren and Jing, Yinan and Wang, X. Sean and Cao, Li and Wan, Mingxiang},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {3},
        pages = {399--412},
        doi = {10.14778/3778092.3778101},
        url = {https://doi.org/10.14778/3778092.3778101},
        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 9 of 9 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers