Leveraging Simple Model Predictions for Enhancing its Performance
share
There has been recent interest in improving performance of simple models for multiple reasons such as interpretability, robust learning from small data, and deployment in memory constrained environments. In this paper, we propose a novel method SRatio that can utilize information from high performing complex models (viz. deep neural networks, boosted trees, random forests) to reweight a training dataset for a potentially low performing simple model such as a decision tree or a shallow network enhancing its performance. Our method also leverages the per sample hardness estimate of the simple model which is not the case with the prior works which primarily consider the complex model's confidences/predictions and is thus conceptually novel. Moreover, we generalize and formalize the concept of attaching probes to intermediate layers of a neural network, which was one of the main ideas in previous work, to other commonly used classifiers and incorporate this into our method. The benefit of these contributions is witnessed in the experiments where on 6 UCI datasets and CIFAR-10 we outperform competitors in a majority (16 out of 27) of the cases and tie for best performance in the remaining cases. In fact, in a couple of cases, we even approach the complex model's performance. We also show for popular loss functions such as cross-entropy loss, least squares loss, and hinge loss that the weighted loss minimized by simple models using our weighting is an upper bound on the loss of the complex model.
READ FULL TEXT
