Learning to Prompt for Continual Learning
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 knowledge 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 sequentially 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 explicitly manage task-invariant and task-specific knowledge while maintaining model plasticity. We conduct comprehensive experiments under popular image classification benchmarks with different challenging continual learning settings, where L2P consistently outperforms prior state-of-the-art methods. Surprisingly, L2P achieves competitive results against rehearsal-based methods even without a rehearsal buffer and is directly applicable to challenging task-agnostic continual learning. Source code is available at https://github.com/google-research/l2p.
Code (5)
Tasks
class-incremental learningClass Incremental LearningContinual Learningimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Learning Probabilistic Prompt for Continual Learning
Continual learning aims to progressively learn from a sequence of tasks, each containing a disjoint subset of classes, while preserving previously learned knowledge. Prompt-based continual learning methods propose to lea…
Continual LearningVector Quantization Prompting for Continual Learning
Continual learning requires to overcome catastrophic forgetting when training a single model on a sequence of tasks. Recent top-performing approaches are prompt-based methods that utilize a set of learnable parameters (i…
Continual LearningQuantizationGenerating Instance-level Prompts for Rehearsal-free Continual Learning
We introduce Domain-Adaptive Prompt (DAP), a novel method for continual learning using Vision Transformers (ViT). Prompt-based continual learning has recently gained attention due to its rehearsal-free nature. Curren…
Continual LearningMM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
Continual Visual Question Answering (CVQA) based on pre-trained models(PTMs) has achieved promising progress by leveraging prompt tuning to enable continual multi-modal learning. However, most existing methods adopt cros…
Continual LearningQuestion AnsweringVisual Question AnsweringProgressive Prompts: Continual Learning for Language Models
We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models. Our method allows forward transfer and resists catastrophic forgetting, without relying on data replay or a la…
Continual Learning