MCGI: Manifold-Consistent Graph Indexing for Billion-Scale Disk-Resident Vector Search

arXiv:2601.01930v3 Announce Type: replace-cross Abstract: Graph-based Approximate Nearest Neighbor (ANN) search often suffers from performance degradation in high-dimensional spaces due to the Euclidean-Geodesic mismatch, where greedy routing diverges from the underlying data manifold. To address this challenge, this paper presents Manifold-Consistent Graph Indexing (MCGI), a geometry-aware and disk-resident indexing method that leverages Local Intrinsic Dimensionality (LID) to dynamically adapt