Back to Search Start Over

Leveraging Hierarchical Taxonomies in Prompt-based Continual Learning

Authors :
Tran, Quyen
Le, Minh
Truong, Tuan
Phung, Dinh
Ngo, Linh
Nguyen, Thien
Ho, Nhat
Le, Trung
Publication Year :
2024

Abstract

Drawing inspiration from human learning behaviors, this work proposes a novel approach to mitigate catastrophic forgetting in Prompt-based Continual Learning 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 the most robust state-of-the-art models on various benchmarks.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2410.04327
Document Type :
Working Paper