Unverified50% confidenceFactExact time
HNSW is short for Hierarchical Navigable Small World, and its predecessor NSW was proposed by the same group of authors; HNSW solves the problem that NSW easily falls into local optima on low-dimensional or strongly clustered data by stacking multiple layers of sparse graphs.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHNSWlib专注于基于分层可导航小世界图（HNSW）的ANN索引，在高召回率场景下性能出色，但内存占用较高且不支持量化压缩66% similarPartially VerifiedHNSW (Hierarchical Navigable Small World graph) is an approximate nearest neighbor search algorithm proposed by Russian scholar Yuri Malkov and others in 2016.57% similarUnverified不同深度学习框架有不同的张量排列约定（NHWC vs NCHW）52% similarVerifiedThe HNSW algorithm was proposed by Yury Malkov and others in 2016, reducing search complexity from O(n) to O(log n) through a multi-layer graph structure.52% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1050492API
curl https://kongchang.com/api/v1/knowledge/claims/1050492MCP
get_claim(id=1050492)