Learning Discriminative Representation with Signed Laplacian Restricted Boltzmann Machine
This work addresses representation learning for supervised tasks, but it appears incremental as it builds on existing RBM methods with specific constraints.
The paper tackled the problem of discriminative representation learning by proposing a Signed Laplacian Restricted Boltzmann Machine (SLRBM) that incorporates class information and preserves data locality, showing effectiveness on benchmark datasets.
We investigate the potential of a restricted Boltzmann Machine (RBM) for discriminative representation learning. By imposing the class information preservation constraints on the hidden layer of the RBM, we propose a Signed Laplacian Restricted Boltzmann Machine (SLRBM) for supervised discriminative representation learning. The model utilizes the label information and preserves the global data locality of data points simultaneously. Experimental results on the benchmark data set show the effectiveness of our method.