Representational Continuity for Unsupervised Continual Learning
This addresses the scalability issue for real-world applications where data is often unannotated and biased, offering a novel approach to continual learning without reliance on labeled data.
The paper tackles the problem of catastrophic forgetting in unsupervised continual learning (UCL) by analyzing feature representations and proposing a technique called Lifelong Unsupervised Mixup (LUMP). It finds that UCL is more robust to forgetting, achieves better performance and generalization than supervised continual learning, and learns smoother loss landscapes.
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.