DLH and DLH-M use distance-aware labeling sets compressed via hashing to support graph range filters in filtered ANN, delivering up to 70.3% higher throughput at over 98.5% recall.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Approximate Nearest Neighbor Search with Graph Range Filters
DLH and DLH-M use distance-aware labeling sets compressed via hashing to support graph range filters in filtered ANN, delivering up to 70.3% higher throughput at over 98.5% recall.