gagolews / genieclust

Genie: Fast and Robust Hierarchical Clustering with Noise Point Detection - in Python and R
https://genieclust.gagolewski.com
Other
58 stars 10 forks source link

Allow approximate NN / EMST #15

Closed gagolews closed 4 years ago

gagolews commented 4 years ago

e.g., http://www.cs.ubc.ca/research/flann/ https://github.com/facebookresearch/faiss or https://github.com/spotify/annoy https://github.com/nmslib/nmslib [NN-descent...] https://github.com/nmslib/hnswlib ; some will also enable sparse input data (e.g., for text mining applications)

gagolews commented 4 years ago
gagolews commented 4 years ago

EMST from mlpack?

gagolews commented 4 years ago
## sipu/worms_2
genieclust.from_distance [4 threads]: 12.274
mlpack.emst: 0.563

## mnist/fashion
genieclust.from_distance [4 threads]: 552.031
mlpack.emst: 3827.782
gagolews commented 4 years ago
##sipu/worms_2
##mlpack.krann: 7.993
##mlpack.lsh: 4.729
##faiss: 30.729

##mnist/fashion
##mlpack.krann: 17.518
##mlpack.lsh: 13.563
##faiss: 131.342
gagolews commented 4 years ago

image

gagolews commented 4 years ago

https://github.com/nmslib/hnswlib/blob/master/README.md

https://github.com/spotify/annoy