Retrieval and search · MLD-0522
HNSW
A graph-based approximate nearest-neighbor method using layered navigable proximity graphs.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Retrieve similar vectors quickly.
Original caveat
Search effort, memory, and recall trade off.
Context and aliases
Level: Intermediate. Stages: Data · Retrieval · Inference · Evaluation.
Tags: ML · NLP · SLM · LLM · IR.
Aliases: Hierarchical navigable small world.
Related concepts
Concepts linking here
Original references
- Faiss documentation ↗ · Reference link
- Efficient and Robust Approximate Nearest Neighbor Search Using HNSW ↗ · Reference link
- Original reference URL ↗