DEG is a graph-based index for hybrid vector queries that keeps edges active only for the query weights where they are useful, preserving accuracy across all weight values.
Kakade, and John Langford
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DB 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DEG: Efficient Hybrid Vector Search Using the Dynamic Edge Navigation Graph
DEG is a graph-based index for hybrid vector queries that keeps edges active only for the query weights where they are useful, preserving accuracy across all weight values.