Gradient Episodic Memory for Continual Learning
This addresses the challenge of catastrophic forgetting in AI models, enabling more efficient learning across tasks, though it is incremental as it builds on existing continual learning approaches.
The paper tackles the problem of continual learning, where models learn from a sequence of tasks without forgetting previous knowledge, by proposing Gradient Episodic Memory (GEM) to reduce forgetting and enable knowledge transfer, achieving strong performance on MNIST and CIFAR-100 variants compared to state-of-the-art methods.
One major obstacle towards AI is the poor ability of models to solve new problems quicker, and without forgetting previously acquired knowledge. To better understand this issue, we study the problem of continual learning, where the model observes, once and one by one, examples concerning a sequence of tasks. First, we propose a set of metrics to evaluate models learning over a continuum of data. These metrics characterize models not only by their test accuracy, but also in terms of their ability to transfer knowledge across tasks. Second, we propose a model for continual learning, called Gradient Episodic Memory (GEM) that alleviates forgetting, while allowing beneficial transfer of knowledge to previous tasks. Our experiments on variants of the MNIST and CIFAR-100 datasets demonstrate the strong performance of GEM when compared to the state-of-the-art.