GrCAN: Gradient Boost Convolutional Autoencoder with Neural Decision Forest
This work addresses classification tasks by integrating deep learning and ensemble methods, but it appears incremental as it builds on existing neural decision forest and gradient boosting techniques.
The authors tackled the problem of combining convolutional autoencoders with neural decision forests to exploit the benefits of both models, and they developed a gradient boost module to improve performance, achieving good efficiency and prediction results on public datasets.
Random forest and deep neural network are two schools of effective classification methods in machine learning. While the random forest is robust irrespective of the data domain, the deep neural network has advantages in handling high dimensional data. In view that a differentiable neural decision forest can be added to the neural network to fully exploit the benefits of both models, in our work, we further combine convolutional autoencoder with neural decision forest, where autoencoder has its advantages in finding the hidden representations of the input data. We develop a gradient boost module and embed it into the proposed convolutional autoencoder with neural decision forest to improve the performance. The idea of gradient boost is to learn and use the residual in the prediction. In addition, we design a structure to learn the parameters of the neural decision forest and gradient boost module at contiguous steps. The extensive experiments on several public datasets demonstrate that our proposed model achieves good efficiency and prediction performance compared with a series of baseline methods.