Proposes Unified Dominance Graph (UDG) for interval-predicate ANNS by mapping to dominance space and building a predicate-specific graph index with patch edges for better search under filters.
Arkgraph: All-range approximate k-nearest-neighbor graph,
3 Pith papers cite this work, alongside 12 external citations. Polarity classification is still indexing.
3
Pith papers citing it
12
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A machine-learned router predicts per-query recall for filtered ANN methods and selects the recall-QPS optimal one, outperforming fixed baselines on five unseen datasets.
FAVOR achieves 1.3-5x higher QPS at 95% Recall@10 for arbitrary filtered ANNS by combining exclusion-distance reshaping in HNSW graphs with a selectivity-driven router that switches between brute-force and optimized search.
citing papers explorer
-
Unified Dominance Graph for Interval-Predicate Approximate Nearest Neighbor Search
Proposes Unified Dominance Graph (UDG) for interval-predicate ANNS by mapping to dominance space and building a predicate-specific graph index with patch edges for better search under filters.
-
Query-aware Routing for Filtered Approximate Nearest Neighbors Search
A machine-learned router predicts per-query recall for filtered ANN methods and selects the recall-QPS optimal one, outperforming fixed baselines on five unseen datasets.
-
FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances
FAVOR achieves 1.3-5x higher QPS at 95% Recall@10 for arbitrary filtered ANNS by combining exclusion-distance reshaping in HNSW graphs with a selectivity-driven router that switches between brute-force and optimized search.