Subset Sampling For Progressive Neural Network Learning
This work addresses the high computational cost of progressive neural network training for machine learning practitioners, though it is incremental in nature.
The paper tackles the computational inefficiency of Progressive Neural Network Learning by proposing subset sampling strategies and online hyperparameter selection, achieving comparable performance to baseline methods while significantly reducing training time.
Progressive Neural Network Learning is a class of algorithms that incrementally construct the network's topology and optimize its parameters based on the training data. While this approach exempts the users from the manual task of designing and validating multiple network topologies, it often requires an enormous number of computations. In this paper, we propose to speed up this process by exploiting subsets of training data at each incremental training step. Three different sampling strategies for selecting the training samples according to different criteria are proposed and evaluated. We also propose to perform online hyperparameter selection during the network progression, which further reduces the overall training time. Experimental results in object, scene and face recognition problems demonstrate that the proposed approach speeds up the optimization procedure considerably while operating on par with the baseline approach exploiting the entire training set throughout the training process.