Stochastic Triplet Embedding



Stochastic Triplet Embedding learns low-dimensional maps based on similarity triplets of the form “A is more similar to B than to C”. It is described in the following paper:

  1. L.J.P. van der Maaten and K.Q. Weinberger. Stochastic Triplet Embedding. To appear in Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing, 2012. [ PDF ]

A large version of the map we constructed based on the music artist similarity data set is available here (1.8 MB).


Code provided by Laurens van der Maaten and Kilian Weinberger, 2012. The authors of this code do not take any responsibility for damage that is the result from bugs in the provided code. This code can be used for non-commercial purposes only. Please contact the authors if you would like to use this code commercially.


The code below contains implementations of crowd-kernel learning, generalized non-metric multidimensional scaling, and (t-distributed) stochastic triplet embedding; as well as code demonstrating how to use these implementations.

  1. Download Matlab code, data, and paper results (.ZIP; 44.4 MB)

NOTE: Please cite our paper if you use this code!

Problems / Bugs / Questions?

Feel free to drop me a line.