One-stage Prompt-based Continual Learning

Youngeun Kim, Yuhang Li, Priyadarshini Panda

Primary Area: transfer learning, meta learning, and lifelong learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Efficient learning, Continual learning, Transfer learning

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We introduce a one-stage Prompt-based Continual Learning (PCL) framework that reduces computational cost while maintaining accuracy compared to the prior two-stage PCL methods.

Abstract: Prompt-based Continual Learning (PCL) has gained considerable attention as a promising continual learning solution as it achieves state-of-the-art performance while preventing privacy violation and memory overhead issues. Nonetheless, existing PCL approaches face significant computational burdens because of two Vision Transformer (ViT) feed-forward stages; one is for the query ViT that generates a prompt query to select prompts inside a prompt pool; the other one is a backbone ViT that mixes information between selected prompts and image tokens. To address this, we introduce a one-stage PCL framework by directly using the intermediate layer's token embedding as a prompt query. This design removes the need for an additional feed-forward stage for query ViT, resulting in $\sim 50\%$ computational cost reduction for both training and inference with marginal accuracy drop ($\le 1\%$). We further introduce a Query-Pool Regularization (QR) loss that regulates the relationship between the prompt query and the prompt pool to improve representation power. The QR loss is only applied during training time, so there is no computational overhead at inference from the QR loss. With the QR loss, our approach maintains $\sim 50\%$ computational cost reduction during inference as well as outperforms the prior two-stage PCL methods by $\sim 1.4\%$ on public class-incremental continual learning benchmarks including CIFAR-100 and ImageNet-R.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1437