PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning

TL;DR

PROL introduces a prompt-based online continual learning method that avoids data replay, maintains high performance with fewer parameters, and is suitable for streaming data scenarios with privacy constraints.

Contribution

It proposes a novel prompt-based approach with a lightweight generator and hard-soft update mechanism for effective rehearsal-free continual learning.

Findings

Outperforms current state-of-the-art methods on multiple datasets.

Requires fewer parameters and maintains moderate training and inference times.

Achieves high accuracy without data replay in streaming scenarios.

Abstract

The data privacy constraint in online continual learning (OCL), where the data can be seen only once, complicates the catastrophic forgetting problem in streaming data. A common approach applied by the current SOTAs in OCL is with the use of memory saving exemplars or features from previous classes to be replayed in the current task. On the other hand, the prompt-based approach performs excellently in continual learning but with the cost of a growing number of trainable parameters. The first approach may not be applicable in practice due to data openness policy, while the second approach has the issue of throughput associated with the streaming data. In this study, we propose a novel prompt-based method for online continual learning that includes 4 main components: (1) single light-weight prompt generator as a general knowledge, (2) trainable scaler-and-shifter as specific knowledge, (3) pre-trained model (PTM) generalization preserving, and (4) hard-soft updates mechanism. Our proposed method achieves significantly higher performance than the current SOTAs in CIFAR100, ImageNet-R, ImageNet-A, and CUB dataset. Our complexity analysis shows that our method requires a relatively smaller number of parameters and achieves moderate training time, inference time, and throughput. For further study, the source code of our method is available at https://github.com/anwarmaxsum/PROL.