Database Paper Browser

Back to papers

RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search

Summary: Shows cross-modal (OOD) queries spatially deviate from base embeddings and their k-NNs are mutually distant, breaking assumptions of existing ANNS graphs. Proposes RoarGraph, a query-distribution–guided projected bipartite graph index that yields up to 3.56× faster search at 90% recall on cross-modal datasets. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13495
Venue
VLDB
Year
2024
Pagerank
5.6131833e-05
Overall Rank
5,233 | 63.60%
DOI
10.14778/3681954.3681959

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 10 of 10 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

Semantically Similar Papers