Keep and Learn: Continual Learning by Constraining the Latent Space for Knowledge Preservation in Neural Networks
This addresses the challenge of sequential learning in privacy-sensitive domains like medical imaging, though it appears incremental as it builds on existing continual learning techniques.
The authors tackled the problem of continual learning under data access restrictions by proposing a method that constrains the latent space to preserve knowledge, showing benefits on CIFAR-10/100 and a chest X-ray dataset compared to prior approaches.
Data is one of the most important factors in machine learning. However, even if we have high-quality data, there is a situation in which access to the data is restricted. For example, access to the medical data from outside is strictly limited due to the privacy issues. In this case, we have to learn a model sequentially only with the data accessible in the corresponding stage. In this work, we propose a new method for preserving learned knowledge by modeling the high-level feature space and the output space to be mutually informative, and constraining feature vectors to lie in the modeled space during training. The proposed method is easy to implement as it can be applied by simply adding a reconstruction loss to an objective function. We evaluate the proposed method on CIFAR-10/100 and a chest X-ray dataset, and show benefits in terms of knowledge preservation compared to previous approaches.