LW2G: Learning Whether to Grow for Prompt-based Continual Learning

TL;DR

LW2G introduces a novel method for prompt-based continual learning that adaptively decides when to grow prompt sets based on task differences, improving efficiency and knowledge sharing.

Contribution

The paper proposes LW2G, a plug-in approach that dynamically grows prompt sets by measuring task differences with HFC, enhancing continual learning performance.

Findings

LW2G outperforms existing prompt-based methods in accuracy.

The dynamic growing approach effectively balances prompt pool size and task adaptation.

Extensive experiments validate the method's efficiency and effectiveness.

Abstract

Recent Prompt-based Continual learning (PCL) has achieved remarkable performance with pre-trained models. These approaches expand a prompt pool by adding a new set of prompts while learning and select the correct set during inference. Previous studies have revealed that learning task-wised prompt sets individually and low selection accuracy pose challenges to the performance of PCL. In this paper, we propose a plug-in method, $\textbf{L}$earning $\textbf{W}$hether $\textbf{t}$o $\textbf{G}$row $\textbf{(LW2G)}$, which leverages the disparities between tasks to form an effective and efficient prompt sets pool, thereby achieving intra-task knowledge sharing and cooperation and avoiding the unbounded increase in the cost of the prompt pool. Specifically, a shared set is utilized when several tasks share certain commonalities, and a new set is added when there are significant differences between the new and previous tasks. To achieve this, we develop a metric called Hinder Forward Capability (HFC) to measure the hindrance imposed on learning new tasks by surgically modifying the original gradient onto the orthogonal complement of the old feature space. With HFC, an automated scheme, Dynamic Growing Approach, adaptively learns whether to grow with a dynamic threshold. Furthermore, we design a gradient-based constraint to ensure consistency between the updating prompts and pre-trained knowledge. Extensive experiments show the effectiveness of our method. Code is available at https://github.com/RAIAN08/LW2G.