RED-ANNS: An RDMA-Enabled Distributed Framework for Graph-Based Approximate Nearest Neighbor Search
Summary: RED-ANNS leverages RDMA to expose a logically full graph in shared memory, avoiding index segmentation and MapReduce-style overhead for distributed ANNS. Combining locality-aware placement, affinity scheduling, and a dependency-relaxed best-first search reduces remote accesses and hides RDMA latency, yielding up to 2.5×–5.3× speedups. (summarized by gpt-5-mini on Mar 13 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yue Chen
- 2. Kai Zhang
- 3. Sipeng Chen
- 4. Shihai Xiao
- 5. Xiaomin Zou
- 6. Ren Ren
- 7. Yinan Jing
- 8. X. Sean Wang
- 9. Li Cao
- 10. Mingxiang Wan
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