DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier
This addresses data scarcity and privacy issues for machine learning practitioners needing to reuse trained models without storing original datasets, though it is incremental as it builds on existing GAN and knowledge distillation methods.
The paper tackles the problem of lacking relevant data for future learning tasks like model compression and incremental learning by proposing DeGAN, a Data-enriching GAN framework that retrieves representative samples from a trained classifier using available data, achieving state-of-the-art performance on benchmark datasets.
In this era of digital information explosion, an abundance of data from numerous modalities is being generated as well as archived everyday. However, most problems associated with training Deep Neural Networks still revolve around lack of data that is rich enough for a given task. Data is required not only for training an initial model, but also for future learning tasks such as Model Compression and Incremental Learning. A diverse dataset may be used for training an initial model, but it may not be feasible to store it throughout the product life cycle due to data privacy issues or memory constraints. We propose to bridge the gap between the abundance of available data and lack of relevant data, for the future learning tasks of a given trained network. We use the available data, that may be an imbalanced subset of the original training dataset, or a related domain dataset, to retrieve representative samples from a trained classifier, using a novel Data-enriching GAN (DeGAN) framework. We demonstrate that data from a related domain can be leveraged to achieve state-of-the-art performance for the tasks of Data-free Knowledge Distillation and Incremental Learning on benchmark datasets. We further demonstrate that our proposed framework can enrich any data, even from unrelated domains, to make it more useful for the future learning tasks of a given network.