Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning

• URL: http://arxiv.org/abs/2404.14607v1
• Date: Mon, 22 Apr 2024 22:04:16 GMT
• Title: Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning
• Authors: Yanhui Guo, Shaoyuan Xu, Jinmiao Fu, Jia Liu, Chaosheng Dong, Bryan Wang,
• Abstract summary: textbfQ-tuning enables lifelong learning of a pre-trained language model. When learning a new task, Q-tuning trains a task-specific prompt by adding it to a prompt queue consisting of the prompts from older tasks.
• Score: 21.261637357094035
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces \textbf{Q-tuning}, a novel approach for continual prompt tuning that enables the lifelong learning of a pre-trained language model. When learning a new task, Q-tuning trains a task-specific prompt by adding it to a prompt queue consisting of the prompts from older tasks. To better transfer the knowledge of old tasks, we design an adaptive knowledge aggregation technique that reweighs previous prompts in the queue with a learnable low-rank matrix. Once the prompt queue reaches its maximum capacity, we leverage a PCA-based eviction rule to reduce the queue's size, allowing the newly trained prompt to be added while preserving the primary knowledge of old tasks. In order to mitigate the accumulation of information loss caused by the eviction, we additionally propose a globally shared prefix prompt and a memory retention regularization based on information theory. Extensive experiments demonstrate that our approach outperforms the state-of-the-art methods substantially on continual prompt tuning benchmarks. Moreover, our approach enables lifelong learning on linearly growing task sequences while requiring constant complexity for training and inference.

Related papers

• Vector Quantization Prompting for Continual Learning [23.26682439914273]
  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 to encode task knowledge. We propose VQ-Prompt, a prompt-based continual learning method that incorporates Vector Quantization into end-to-end training of a set of discrete prompts.
  arXiv  Detail & Related papers  (2024-10-27T13:43:53Z)
• LW2G: Learning Whether to Grow for Prompt-based Continual Learning [15.766350352592331]
  Recent Prompt-based Continual Learning (PCL) has achieved remarkable performance with Pre-Trained Models (PTMs) We propose a plug-in module in the former stage to textbfLearn Whether to Grow (LW2G) based on the disparities between tasks. Inspired by Gradient Projection Continual Learning, our LW2G develops a metric called Hinder Forward Capability (HFC) to measure the hindrance imposed on learning new tasks.
  arXiv  Detail & Related papers  (2024-09-27T15:55:13Z)
• PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer [76.39111896665585]
  Incremental Learning (IL) aims to learn deep models on sequential tasks continually. Recent vast pre-trained models (PTMs) have achieved outstanding performance by prompt technique in practical IL without the old samples.
  arXiv  Detail & Related papers  (2024-07-04T10:37:58Z)
• Hierarchical Prompts for Rehearsal-free Continual Learning [67.37739666753008]
  Continual learning endeavors to equip the model with the capability to integrate current task knowledge while mitigating the forgetting of past task knowledge. Inspired by prompt tuning, prompt-based methods maintain a frozen backbone and train with slight learnable prompts. This paper introduces a novel rehearsal-free paradigm for continual learning termed Hierarchical Prompts (H-Prompts)
  arXiv  Detail & Related papers  (2024-01-21T16:59:44Z)
• Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks [101.40633115037983]
  Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions. How to select new tasks to improve the performance and generalizability of IT models remains an open question. We propose active instruction tuning based on prompt uncertainty, a novel framework to identify informative tasks, and then actively tune the models on the selected tasks.
  arXiv  Detail & Related papers  (2023-11-01T04:40:05Z)
• Self-regulating Prompts: Foundational Model Adaptation without Forgetting [112.66832145320434]
  We introduce a self-regularization framework for prompting called PromptSRC. PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations.
  arXiv  Detail & Related papers  (2023-07-13T17:59:35Z)
• Task Residual for Tuning Vision-Language Models [69.22958802711017]
  We propose a new efficient tuning approach for vision-language models (VLMs) named Task Residual Tuning (TaskRes) TaskRes explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task. The proposed TaskRes is simple yet effective, which significantly outperforms previous methods on 11 benchmark datasets.
  arXiv  Detail & Related papers  (2022-11-18T15:09:03Z)
• Continual Prompt Tuning for Dialog State Tracking [58.66412648276873]
  A desirable dialog system should be able to continually learn new skills without forgetting old ones. We present Continual Prompt Tuning, a parameter-efficient framework that not only avoids forgetting but also enables knowledge transfer between tasks.
  arXiv  Detail & Related papers  (2022-03-13T13:22:41Z)
• TAG: Task-based Accumulated Gradients for Lifelong learning [21.779858050277475]
  We propose a task-aware system that adapts the learning rate based on the relatedness among tasks. We empirically show that our proposed adaptive learning rate not only accounts for catastrophic forgetting but also allows positive backward transfer.
  arXiv  Detail & Related papers  (2021-05-11T16:10:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.