The kernel of graph indices for vector search
Mariano Tepper, Ted Willke

TL;DR
This paper introduces the Support Vector Graph (SVG), a novel graph index for vector search that uses kernel methods to ensure navigability in both metric and non-metric spaces, improving upon existing methods.
Contribution
The paper proposes SVG, a new graph index leveraging kernel methods for broader applicability, and introduces SVG-L0 with sparsity constraints for practical, bounded out-degree graphs.
Findings
SVG provides formal navigability guarantees in diverse vector spaces.
SVG encompasses and generalizes popular indices like HNSW and DiskANN.
SVG-L0 achieves bounded out-degree with self-tuning and efficient complexity.
Abstract
The most popular graph indices for vector search use principles from computational geometry to build the graph. Hence, their formal graph navigability guarantees are only valid in Euclidean space. In this work, we show that machine learning can be used to build graph indices for vector search in metric and non-metric vector spaces (e.g., for inner product similarity). From this novel perspective, we introduce the Support Vector Graph (SVG), a new type of graph index that leverages kernel methods to establish the graph connectivity and that comes with formal navigability guarantees valid in metric and non-metric vector spaces. In addition, we interpret the most popular graph indices, including HNSW and DiskANN, as particular specializations of SVG and show that new navigable indices can be derived from the principles behind this specialization. Finally, we propose SVG-L0 that…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGraph Labeling and Dimension Problems
MethodsSparse Evolutionary Training
