MCGI adapts graph-based vector search to data manifolds via local intrinsic dimensionality to improve approximation quality and stability at billion scale.
Let s=∥u−v∥ be the distance between the current node and the candidate neighbor (the step size)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MCGI: Manifold-Consistent Graph Indexing for Billion-Scale Disk-Resident Vector Search
MCGI adapts graph-based vector search to data manifolds via local intrinsic dimensionality to improve approximation quality and stability at billion scale.