Engineering Efficient and Effective Non-metric Space Library

130 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs (2016, methodology): “The Hierarchical NSW algorithm was implemented in Cþþ on top of the Non-Metric Space Library (nmslib) [49](1), which already had an NSW implementation (under name “sw-graph”).”
Learning to Prune in Metric and Non-Metric Spaces (2013, methodology): “The software (including scripts that can be used to reproduce our results) is available online, as a part of the Non-Metric Space Library2 [5].”
Comparative Analysis of Data Structures for Approximate Nearest Neighbor Search (2014, methodology): “60 GHz, 32GB memory) in a single threaded mode using the Non-Metric Space Library as an evaluation toolkit [12].”
Towards Neural Theorem Proving at Scale (2018, methodology): “In this work we use Hierarchical Navigable Small World (HNSW) (Malkov and Yashunin, 2016; Boytsov and Naidan, 2013), a graph-based incremental ANNS structure which can offer much better logarithmic complexity scaling in comparison with other approaches.”