Exploiting Hierarchical Taxonomies in Pretrained Continual Learning

Quyen Tran, Minh Le, Tuan Truong, Dinh Phung, Linh Van Ngo, Thien Huu Nguyen, Nhat Ho, Trung Le

Keywords: pretrained continual learning

TL;DR: Drawing inspiration from human learning behaviors, this work proposes a novel approach to mitigate catastrophic forgetting in Prompt-based Continual Learning models, focusing on exploiting the relationships between continuously emerging class data.

Abstract:

Drawing inspiration from human learning behaviors, this work proposes a novel approach to mitigate catastrophic forgetting in Prompt-based Continual Learning (PCL) models by exploiting the relationships between continuously emerging class data. We find that applying human habits of organizing and connecting information can serve as an efficient strategy when training deep learning models.
Specifically, by building a hierarchical tree structure based on the expanding set of labels, we gain fresh insights into the data, identifying groups of similar classes could easily cause confusion. Additionally, we delve deeper into the hidden connections between classes by exploring the original pretrained model’s behavior through an optimal transport-based approach. From these insights, we propose
a novel regularization loss function that encourages models to focus more on challenging knowledge areas, thereby enhancing overall performance. Experimentally, our method demonstrated significant superiority over current state-of-the-arts on various benchmarks.

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.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

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: 1156