KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All

TL;DR

KOPPA introduces a novel key-query orthogonal projection and prototype-based classification to improve prompt-based continual learning, significantly outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a new key-query learning strategy with orthogonal projection and a prototype-based component for better task separation in continual learning.

Findings

Achieves up to 20% performance improvement over state-of-the-art methods.

Effectively addresses feature shift and task separation issues.

Enhances prompt matching efficiency in continual learning scenarios.

Abstract

Drawing inspiration from prompt tuning techniques applied to Large Language Models, recent methods based on pre-trained ViT networks have achieved remarkable results in the field of Continual Learning. Specifically, these approaches propose to maintain a set of prompts and allocate a subset of them to learn each task using a key-query matching strategy. However, they may encounter limitations when lacking control over the correlations between old task queries and keys of future tasks, the shift of features in the latent space, and the relative separation of latent vectors learned in independent tasks. In this work, we introduce a novel key-query learning strategy based on orthogonal projection, inspired by model-agnostic meta-learning, to enhance prompt matching efficiency and address the challenge of shifting features. Furthermore, we introduce a One-Versus-All (OVA) prototype-based component that enhances the classification head distinction. Experimental results on benchmark datasets demonstrate that our method empowers the model to achieve results surpassing those of current state-of-the-art approaches by a large margin of up to 20%.