La-MAML: Look-ahead Meta Learning for Continual Learning
The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks. While meta-learning shows great potential for reducing interference between old and new tasks, the current training procedures tend to be either slow or offline, and sensitive to many hyper-parameters. In this work, we propose Look-ahead MAML (La-MAML), a fast optimisation-based meta-learning algorithm for online-continual learning, aided by a small episodic memory. Our proposed modulation of per-parameter learning rates in our meta-learning update allows us to draw connections to prior work on hypergradients and meta-descent. This provides a more flexible and efficient way to mitigate catastrophic forgetting compared to conventional prior-based methods. La-MAML achieves performance superior to other replay-based, prior-based and meta-learning based approaches for continual learning on real-world visual classification benchmarks. Source code can be found here: https://github.com/montrealrobotics/La-MAML
Code (3)
Tasks
Continual LearningMeta-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Look-ahead Meta Learning for Continual Learning
The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks. While meta-learning shows great potential for reducing interfer…
Continual LearningMeta-LearningReproducibility Report: La-MAML: Look-ahead Meta Learning for Continual Learning
The Continual Learning (CL) problem involves performing well on a sequence of tasks under limited compute. Current algorithms in the domain are either slow, offline or sensitive to hyper-parameters. La-MAML, an optimizat…
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-LearningOnline 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-LearningMemory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning
In recent years, model-agnostic meta-learning (MAML) has become a popular research area. However, the stochastic optimization of MAML is still underdeveloped. Existing MAML algorithms rely on the ``episode'' idea by samp…
Continual LearningFederated LearningMeta-LearningPersonalized Federated Learning+1