Prompt Customization for Continual Learning
This work addresses noise issues in prompt-based continual learning, offering a novel method that improves performance for incremental learning tasks, though it is incremental in nature.
The paper tackles the problem of noise in prompt selection for continual learning by proposing a prompt customization method with generation and modulation modules, achieving up to 16.2% improvement over state-of-the-art techniques on benchmark datasets.
Contemporary continual learning approaches typically select prompts from a pool, which function as supplementary inputs to a pre-trained model. However, this strategy is hindered by the inherent noise of its selection approach when handling increasing tasks. In response to these challenges, we reformulate the prompting approach for continual learning and propose the prompt customization (PC) method. PC mainly comprises a prompt generation module (PGM) and a prompt modulation module (PMM). In contrast to conventional methods that employ hard prompt selection, PGM assigns different coefficients to prompts from a fixed-sized pool of prompts and generates tailored prompts. Moreover, PMM further modulates the prompts by adaptively assigning weights according to the correlations between input data and corresponding prompts. We evaluate our method on four benchmark datasets for three diverse settings, including the class, domain, and task-agnostic incremental learning tasks. Experimental results demonstrate consistent improvement (by up to 16.2\%), yielded by the proposed method, over the state-of-the-art (SOTA) techniques.