File:Hierarchical Navigable Small World (HNSW).png
Size of this preview: 800 × 337 pixels. Other resolutions: 320 × 135 pixels | 640 × 269 pixels | 1,024 × 431 pixels | 1,280 × 538 pixels | 2,520 × 1,060 pixels.
Original file (2,520 × 1,060 pixels, file size: 511 KB, MIME type: image/png)
This is a file from the Wikimedia Commons. Information from its description page there is shown below.
Commons is a freely licensed media file repository. You can help.
.png){kind=link}
Commons is a freely licensed media file repository. You can help.
Summary
| Description |
English: This diagram shows the core idea of a Hierarchical Navigable Small World (HNSW) graph, an algorithm for efficient approximate nearest-neighbor search in high-dimensional vector spaces. The structure is multi-layered: the top layer (Layer 2) is the sparsest and provides an entry point. The closest node found in each layer is used as the entry point for the subsequent, denser layer. HNSW is a multi-level graph index over the vector space; each layer is a coarser (sparser) or finer (denser) level of the index used during search. |
| Date | |
| Source | Own work |
| Author | Rose electric |
Licensing
I, the copyright holder of this work, hereby publish it under the following license:
This file is licensed under the Creative Commons Attribution 4.0 International license.
- You are free:
- to share – to copy, distribute and transmit the work
- to remix – to adapt the work
- Under the following conditions:
- attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
File history
Click on a date/time to view the file as it appeared at that time.
| Date/Time | Thumbnail | Dimensions | User | Comment | |
|---|---|---|---|---|---|
| current | 05:58, 8 September 2025 | | 2,520 × 1,060 (511 KB) | Rose electric | Uploaded own work with UploadWizard |
File usage
The following page uses this file:
.png?lang=en){kind=link}