Friendly Training: Neural Networks Can Adapt Data To Make Learning Easier

TL;DR

Friendly Training introduces a novel approach where training data are adaptively simplified during neural network training, leading to improved learning stability and generalization, especially in deep convolutional models.

Contribution

This paper presents a new data adaptation method called Friendly Training, which simplifies difficult examples during training to enhance neural network learning.

Findings

Improves training stability and generalization in neural networks.

Outperforms random and informed data sub-selection methods.

Effective especially in deep convolutional architectures.

Abstract

In the last decade, motivated by the success of Deep Learning, the scientific community proposed several approaches to make the learning procedure of Neural Networks more effective. When focussing on the way in which the training data are provided to the learning machine, we can distinguish between the classic random selection of stochastic gradient-based optimization and more involved techniques that devise curricula to organize data, and progressively increase the complexity of the training set. In this paper, we propose a novel training procedure named Friendly Training that, differently from the aforementioned approaches, involves altering the training examples in order to help the model to better fulfil its learning criterion. The model is allowed to simplify those examples that are too hard to be classified at a certain stage of the training procedure. The data transformation is controlled by a developmental plan that progressively reduces its impact during training, until it completely vanishes. In a sense, this is the opposite of what is commonly done in order to increase robustness against adversarial examples, i.e., Adversarial Training. Experiments on multiple datasets are provided, showing that Friendly Training yields improvements with respect to informed data sub-selection routines and random selection, especially in deep convolutional architectures. Results suggest that adapting the input data is a feasible way to stabilize learning and improve the generalization skills of the network.