Meta-Learning Representations for Continual Learning

Abstract

A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguably do the opposite---they are highly prone to forgetting and rarely trained to facilitate future learning. One reason for this poor behavior is that they learn from a representation that is not explicitly trained for these two goals. In this paper, we propose OML, an objective that directly minimizes catastrophic interference by learning representations that accelerate future learning and are robust to forgetting under online updates in continual learning. We show that it is possible to learn naturally sparse representations that are more effective for online updating. Moreover, our algorithm is complementary to existing continual learning strategies, such as MER and GEM. Finally, we demonstrate that a basic online updating strategy on representations learned by OML is competitive with rehearsal based methods for continual learning. We release an implementation of our method at https://github.com/khurramjaved96/mrcl .

Accepted at NeurIPS19, 15 pages, 10 figures, open-source, representation learning, continual learning, online learning

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Continual Learning Through Synaptic Intelligence
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Efficient Lifelong Learning with A-GEM
• On Tiny Episodic Memories in Continual Learning
• Overcoming Catastrophic Forgetting by Incremental Moment Matching
• A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Selfless Sequential Learning
• Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL

Cited by in corpus (7)

• Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• On-device Training: A First Overview on Existing Systems
• Regularizing Deep Multi-Task Networks using Orthogonal Gradients
• Defining Benchmarks for Continual Few-Shot Learning
• Meta-learnt priors slow down catastrophic forgetting in neural networks
• Block Contextual MDPs for Continual Learning
• Meta-Learning to Improve Pre-Training