Improved Schemes for Episodic Memory-based Lifelong Learning
arXiv:1909.11763
Abstract
Current deep neural networks can achieve remarkable performance on a single task. However, when the deep neural network is continually trained on a sequence of tasks, it seems to gradually forget the previous learned knowledge. This phenomenon is referred to as \textit{catastrophic forgetting} and motivates the field called lifelong learning. Recently, episodic memory based approaches such as GEM \cite{lopez2017gradient} and A-GEM \cite{chaudhry2018efficient} have shown remarkable performance. In this paper, we provide the first unified view of episodic memory based approaches from an optimization's perspective. This view leads to two improved schemes for episodic memory based lifelong learning, called MEGA-I and MEGA-II. MEGA-I and MEGA-II modulate the balance between old tasks and the new task by integrating the current gradient with the gradient computed on the episodic memory. Notably, we show that GEM and A-GEM are degenerate cases of MEGA-I and MEGA-II which consistently put the same emphasis on the current task, regardless of how the loss changes over time. Our proposed schemes address this issue by using novel loss-balancing updating rules, which drastically improve the performance over GEM and A-GEM. Extensive experimental results show that the proposed schemes significantly advance the state-of-the-art on four commonly used lifelong learning benchmarks, reducing the error by up to 18\%.
arXiv commentNeurIPS 2020, Spotlight. 17 pages. Code: https://github.com/yunhuiguo/MEGA
References in corpus (19)
- Overcoming catastrophic forgetting in neural networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
- Continual Learning Through Synaptic Intelligence
- Efficient Lifelong Learning with A-GEM
- Multi-Task Learning as Multi-Objective Optimization
- One-shot Learning with Memory-Augmented Neural Networks
- Variational Continual Learning
- Overcoming Catastrophic Forgetting by Incremental Moment Matching
- Measuring Catastrophic Forgetting in Neural Networks
- Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
- Towards Robust Evaluations of Continual Learning
- An Empirical Study of Example Forgetting during Deep Neural Network Learning
- Gradient Surgery for Multi-Task Learning
- Functional Regularisation for Continual Learning with Gaussian Processes
- Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
- A Unifying Bayesian View of Continual Learning
- Toward Understanding Catastrophic Forgetting in Continual Learning