Learning to Active Learn by Gradient Variation based on Instance Importance

A major challenge in active learning is to select the most informative instances to be labeled by an annotation oracle at each step. In this respect, one effective paradigm is to learn the active learning strategy that best suits the performance of a meta-learning model. This strategy first measures the quality of the instances selected in the previous steps and then trains a machine learning model that is used to predict the quality of instances to be labeled in the current step.In this paper, we propose a new approach of learning-to-active-learn that selects the instances to be labeled as the ones producing the maximum change to the current classifier. Our key idea is to select such instances according to their importance reflecting variations in the learning gradient of the classification model. Our approach can be instantiated with any classifier trainable via gradient descent optimization, and here we provide a formulation based on a deep neural network model, which has not deeply been investigated in existing learning-to-active-learn approaches. The experimental validation of our approach has shown promising results in scenarios characterized by relatively few initially labeled instances.