Continual learning with hypernetworks

Johannes von Oswald, Christian Henning, João Sacramento, Benjamin F. Grewe

Keywords: capacity, catastrophic forgetting, continual learning, hypernetworks, memory, transfer learning

Thurs Session 3 (12:00-14:00 GMT) [Live QA] [Cal]
Thurs Session 4 (17:00-19:00 GMT) [Live QA] [Cal]
Thursday: Continual Learning and Few Shot Learning
Thursday: Continual Learning and Few Shot Learning

Abstract: Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate the weights of a target model based on task identity. Continual learning (CL) is less difficult for this class of models thanks to a simple key feature: instead of recalling the input-output relations of all previously seen data, task-conditioned hypernetworks only require rehearsing task-specific weight realizations, which can be maintained in memory using a simple regularizer. Besides achieving state-of-the-art performance on standard CL benchmarks, additional experiments on long task sequences reveal that task-conditioned hypernetworks display a very large capacity to retain previous memories. Notably, such long memory lifetimes are achieved in a compressive regime, when the number of trainable hypernetwork weights is comparable or smaller than target network size. We provide insight into the structure of low-dimensional task embedding spaces (the input space of the hypernetwork) and show that task-conditioned hypernetworks demonstrate transfer learning. Finally, forward information transfer is further supported by empirical results on a challenging CL benchmark based on the CIFAR-10/100 image datasets.

Similar Papers

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut,
Dynamic Model Pruning with Feedback
Tao Lin, Sebastian U. Stich, Luis Barba, Daniil Dmitriev, Martin Jaggi,
MEMO: A Deep Network for Flexible Combination of Episodic Memories
Andrea Banino, Adrià Puigdomènech Badia, Raphael Köster, Martin J. Chadwick, Vinicius Zambaldi, Demis Hassabis, Caswell Barry, Matthew Botvinick, Dharshan Kumaran, Charles Blundell,