Learning to Prompt for Continual Learning

By Zifeng Wang, Zizhao Zhang, Chen-Yu Lee, Han Zhang, Ruoxi Sun, Xiaoqi Ren, Guolong Su, Vincent Perot, Jennifer G. Dy, Tomas Pfister. 2021

1,330 citations recorded by the source corpus.

The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known task identity at test time to retrieve learned knowl-edge and address forgetting, while this work presents a new paradigm for continual learning that aims to train a more succinct memory system without accessing task identity at test time. Our method learns to dynamically prompt (L2P) a pre-trained model to learn tasks sequen-tially under different task transitions. In our proposed framework, prompts are small learnable parameters, which are maintained in a memory space. The objective is to optimize prompts to instruct the model prediction and ex-plicitly manage task-invariant and task-specific knowledge while maintaining model plasticity. We conduct comprehen-sive experiments under popular image classification bench-marks with different challenging continual learning set-tings, where L2P consistently outperforms prior state-of-the-art methods. Surprisingly, L2P achieves competitive results against rehearsal-based methods even without a re-hearsal buffer and is directly applicable to challenging task-agnostic continual learning. Source code is available at https://github.com/google-research/12p.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Prompting & Reasoning, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Dacheng Tao
  2. Mohit Bansal
  3. Han-Jia Ye
  4. De-chuan Zhan
  5. Jun Zhu
  6. Jianfeng Gao
  7. Bernt Schiele
  8. Yoshua Bengio

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Ming-Hsuan Yang
  4. Bernt Schiele
  5. Trevor Darrell
  6. Yi Yang
  7. Xiaogang Wang
  8. Andrew Zisserman

In Prompting & Reasoning

  1. De-chuan Zhan
  2. Da-Wei Zhou
  3. Han-Jia Ye
  4. Wu-Jun Li
  5. Yan-Shuo Liang
  6. Ziwei Liu
  7. Qiwen Wang
  8. Zhiwu Huang

In Meta & Continual Learning

  1. Han-Jia Ye
  2. De-chuan Zhan
  3. Da-Wei Zhou
  4. Liyuan Wang
  5. Xingxing Zhang
  6. Jun Zhu
  7. Hang Su
  8. Gyuhak Kim

Citations in the corpus