Gradient Episodic Memory for Continual Learning

TL;DR

This paper introduces Gradient Episodic Memory (GEM), a novel continual learning model that reduces forgetting and enhances knowledge transfer across tasks, evaluated with new metrics on MNIST and CIFAR-100 variants.

Contribution

The paper proposes GEM, a new continual learning approach, along with metrics to evaluate transfer and forgetting, demonstrating superior performance over existing methods.

Findings

GEM significantly reduces catastrophic forgetting.

GEM improves knowledge transfer across tasks.

Experimental results outperform state-of-the-art methods.

Abstract

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.