Spanning tree approximations for conditional random fields
Patrick Pletscher, Cheng Soon Ong, Joachim M. Buhmann · 2009
In this work we show that one can train Con-ditional Random Fields of intractable graphs effectively and efficiently by considering a mixture of random spanning trees of the un-derlying graphical model. Furthermore, we show how a maximum-likelihood estimator of such a training objective can subsequently be used for prediction on the full graph. We present experimental results which im-prove on the state-of-the-art. Additionally, the training objective is less sensitive to the regularization than pseudo-likelihood based training approaches. We perform the experi-mental validation on two classes of data sets where structure is important: image denois-ing and multilabel classification. 1