Representational Continuity for Unsupervised Continual Learning

TL;DR

This paper explores unsupervised continual learning, demonstrating that it can learn robust, generalizable visual representations without labels, and introduces a new technique called LUMP to reduce forgetting.

Contribution

It provides a systematic analysis of unsupervised representations in continual learning and proposes LUMP, a novel method to mitigate catastrophic forgetting in this setting.

Findings

Unsupervised representations are more robust to forgetting than supervised ones.

UCL achieves better out-of-distribution generalization.

LUMP effectively reduces catastrophic forgetting.

Abstract

Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable to real-world applications where the data distribution is often biased and unannotated. In this work, we focus on unsupervised continual learning (UCL), where we learn the feature representations on an unlabelled sequence of tasks and show that reliance on annotated data is not necessary for continual learning. We conduct a systematic study analyzing the learned feature representations and show that unsupervised visual representations are surprisingly more robust to catastrophic forgetting, consistently achieve better performance, and generalize better to out-of-distribution tasks than SCL. Furthermore, we find that UCL achieves a smoother loss landscape through qualitative analysis of the learned representations and learns meaningful feature representations. Additionally, we propose Lifelong Unsupervised Mixup (LUMP), a simple yet effective technique that interpolates between the current task and previous tasks' instances to alleviate catastrophic forgetting for unsupervised representations.