# PromptFusion: Decoupling Stability and Plasticity for Continual Learning

Source: [PromptFusion: Decoupling Stability and Plasticity for Continual Learning](<https://www.sota2.com/research/paper/68fa74101e209131cea5f8e9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:36:01.778Z

Authors: Haoran Chen, Zuxuan Wu, Xintong Han, Menglin Jia, Yu-Gang Jiang

Published: 2023-03-13T15:58:00.000Z

## Abstract

Current research on continual learning mainly focuses on relieving catastrophic forgetting, and most of their success is at the cost of limiting the performance of newly incoming tasks. Such a trade-off is referred to as the stability-plasticity dilemma and is a more general and challenging problem for continual learning. However, the inherent conflict between these two concepts makes it seemingly impossible to devise a satisfactory solution to both of them simultaneously. Therefore, we ask, "is it possible to divide them into two separate problems to conquer them independently?". To this end, we propose a prompt-tuning-based method termed PromptFusion to enable the decoupling of stability and plasticity. Specifically, PromptFusion consists of a carefully designed \\stab module that deals with catastrophic forgetting and a \\boo module to learn new knowledge concurrently. Furthermore, to address the computational overhead brought by the additional architecture, we propose PromptFusion-Lite which improves PromptFusion by dynamically determining whether to activate both modules for each input image. Extensive experiments show that both PromptFusion and PromptFusion-Lite achieve promising results on popular continual learning datasets for class-incremental and domain-incremental settings. Especially on Split-Imagenet-R, one of the most challenging datasets for class-incremental learning, our method can exceed state-of-the-art prompt-based methods by more than 5\\% in accuracy, with PromptFusion-Lite using 14.8\\% less computational resources than PromptFusion.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2303.07223>)

[PDF](<https://arxiv.org/pdf/2303.07223.pdf>)
