GATE trains a two-tower model to recommend entry points in a proximity graph, cutting search path length and improving query speed by 1.2-2.0x across benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Empowering Graph-based Approximate Nearest Neighbor Search with Adaptive Awareness Capabilities
GATE trains a two-tower model to recommend entry points in a proximity graph, cutting search path length and improving query speed by 1.2-2.0x across benchmarks.