TL;DR
HENN is a new hierarchical graph structure for approximate nearest neighbor search that offers strong theoretical guarantees on query time and high recall, while being practical and scalable for real-world data.
Contribution
HENN combines $ ext{ε}$-net theory with hierarchical graph design to provide provable polylogarithmic query time and high recall, addressing limitations of prior heuristic and theoretical methods.
Findings
HENN achieves faster query times than existing methods.
HENN maintains high recall across diverse and adversarial datasets.
Theoretical analysis confirms polylogarithmic worst-case query time.
Abstract
Hierarchical graph-based algorithms such as HNSW have achieved state-of-the-art performance for Approximate Nearest Neighbor (ANN) search in practice, yet they often lack theoretical guarantees on query time or recall due to their heavy use of randomized heuristic constructions. Conversely, existing theoretically grounded structures are typically difficult to implement and struggle to scale in real-world scenarios. We propose the Hierarchical -Net Navigation Graph (HENN), a novel graph-based indexing structure for ANN search that combines strong theoretical guarantees with practical efficiency. Built upon the theory of -nets, HENN guarantees polylogarithmic worst-case query time while preserving high recall and incurring minimal implementation overhead. Moreover, we establish a probabilistic polylogarithmic query time bound for HNSW, providing theoretical…
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.
