Continual Unsupervised Representation Learning
arXiv:1910.14481
Abstract
Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised or reinforcement learning tasks, and often assumes full knowledge of task labels and boundaries. In this work, we propose an approach (CURL) to tackle a more general problem that we will refer to as unsupervised continual learning. The focus is on learning representations without any knowledge about task identity, and we explore scenarios when there are abrupt changes between tasks, smooth transitions from one task to another, or even when the data is shuffled. The proposed approach performs task inference directly within the model, is able to dynamically expand to capture new concepts over its lifetime, and incorporates additional rehearsal-based techniques to deal with catastrophic forgetting. We demonstrate the efficacy of CURL in an unsupervised learning setting with MNIST and Omniglot, where the lack of labels ensures no information is leaked about the task. Further, we demonstrate strong performance compared to prior art in an i.i.d setting, or when adapting the technique to supervised tasks such as incremental class learning.
NeurIPS 2019
Cited by in corpus (6)
- Learning latent representations across multiple data domains using Lifelong VAEGAN
- Modelling Latent Skills for Multitask Language Generation
- Bayesian Structure Adaptation for Continual Learning
- Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer
- Continual Learning from the Perspective of Compression
- Semi-Supervised Class Discovery