Continual Learning with Deep Generative Replay

TL;DR

This paper introduces Deep Generative Replay, a novel approach to continual learning that uses a generative model to replay past data, mitigating catastrophic forgetting without storing all previous data.

Contribution

It proposes a dual model architecture inspired by hippocampal memory, enabling effective rehearsal of past tasks in sequential learning scenarios.

Findings

Reduces catastrophic forgetting in image classification tasks

Requires less memory than storing all past data

Effective in various sequential learning settings

Abstract

Attempts to train a comprehensive artificial intelligence capable of solving multiple tasks have been impeded by a chronic problem called catastrophic forgetting. Although simply replaying all previous data alleviates the problem, it requires large memory and even worse, often infeasible in real world applications where the access to past data is limited. Inspired by the generative nature of hippocampus as a short-term memory system in primate brain, we propose the Deep Generative Replay, a novel framework with a cooperative dual model architecture consisting of a deep generative model ("generator") and a task solving model ("solver"). With only these two models, training data for previous tasks can easily be sampled and interleaved with those for a new task. We test our methods in several sequential learning settings involving image classification tasks.