Meta Continual Learning
Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This ability is limited in the current deep neural networks by a problem called catastrophic forgetting, where training on new tasks tends to severely degrade performance on previous tasks. One way to lessen the impact of the forgetting problem is to constrain parameters that are important to previous tasks to stay close to the optimal parameters. Recently, multiple competitive approaches for computing the importance of the parameters with respect to the previous tasks have been presented. In this paper, we propose a learning to optimize algorithm for mitigating catastrophic forgetting. Instead of trying to formulate a new constraint function ourselves, we propose to train another neural network to predict parameter update steps that respect the importance of parameters to the previous tasks. In the proposed meta-training scheme, the update predictor is trained to minimize loss on a combination of current and past tasks. We show experimentally that the proposed approach works in the continual learning setting.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningSimilar Papers 제목 키워드 기반
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
Continual learning agents experience a stream of (related) tasks. The main challenge is that the agent must not forget previous tasks and also adapt to novel tasks in the stream. We are interested in the intersection of …
Continual LearningMeta-LearningOnline Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continu…
Continual LearningMeta-LearningLearning to Learn for Few-shot Continual Active Learning
Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting…
Active LearningContinual LearningMeta-Learningtext-classification+1Improving Meta-Continual Learning Representations with Representation Replay
Continual learning often suffers from catastrophic forgetting. Recently, meta-continual learning algorithms use meta-learning to learn how to continually learn. A recent state-of-the-art is online aware meta-learning (OM…
Continual LearningMeta-LearningCoMPS: Continual Meta Policy Search
We develop a new continual meta-learning method to address challenges in sequential multi-task learning. In this setting, the agent's goal is to achieve high reward over any sequence of tasks quickly. Prior meta-reinforc…
Continual Learningcontinuous-controlContinuous ControlMeta-Learning+5