Bayesian Online Multilabel Classification (BOMC)


version 1.0

September 29, 2011


BOMC is an open source toolkit  for online multilabel classification using Bayesian models [1, 2].  It is implemented in F# on Microsoft Visual Studio 2008, and can be compiled and run on Linux systems via Mono.  The graphical model, as shown in Figure 1~3 of [1], is extend from TrueSkillTM [2] to deal with multilabel, and the inference engine is expectation propagation.

We refer the interested users to two other illustrative F# implementations of TrueSkillTM : original [2] and temporal [3].


BOMC version 1.0


BOMC is licensed under Mozilla Public License version 1.1. The authors are not responsible for any implications from the use of the software.


Xinhua Zhang | Thore Graepel | Ralf Herbrich



Xinhua Zhang, Thore Graepel, Ralf Herbrich

Bayesian Online Learning for Multi-label and Multi-variate Performance Measures

International Conference on Artificial Intelligence and Statistics (AISTATS), 2010. [PDF]

[2] Ralf Herbrich, Tom Minka, Thore Graepel
TrueskillTM: A Bayesian skill ranking system.
Neural Information Processing Systems (NIPS) 2007. 
[3] Pierre Dangauthier, Ralf Herbrich, Tom Minka, and Thore Graepel
TrueskillTM: Through Time: Revisiting the History of Chess.
Neural Information Processing Systems (NIPS) 2008. 

Last modified: 29 September, 2011