Hierarchical Prompts for Rehearsal-free Continual Learning

• URL: http://arxiv.org/abs/2401.11544v1
• Date: Sun, 21 Jan 2024 16:59:44 GMT
• Title: Hierarchical Prompts for Rehearsal-free Continual Learning
• Authors: Yukun Zuo, Hantao Yao, Lu Yu, Liansheng Zhuang, Changsheng Xu
• Abstract summary: 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)
• Score: 67.37739666753008
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 to minimize the catastrophic forgetting that arises due to updating a large number of backbone parameters. Nonetheless, these learnable prompts tend to concentrate on the discriminatory knowledge of the current task while ignoring past task knowledge, leading to that learnable prompts still suffering from catastrophic forgetting. This paper introduces a novel rehearsal-free paradigm for continual learning termed Hierarchical Prompts (H-Prompts), comprising three categories of prompts -- class prompt, task prompt, and general prompt. To effectively depict the knowledge of past classes, class prompt leverages Bayesian Distribution Alignment to model the distribution of classes in each task. To reduce the forgetting of past task knowledge, task prompt employs Cross-task Knowledge Excavation to amalgamate the knowledge encapsulated in the learned class prompts of past tasks and current task knowledge. Furthermore, general prompt utilizes Generalized Knowledge Exploration to deduce highly generalized knowledge in a self-supervised manner. Evaluations on two benchmarks substantiate the efficacy of the proposed H-Prompts, exemplified by an average accuracy of 87.8% in Split CIFAR-100 and 70.6% in Split ImageNet-R.

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)
• 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)
• Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning [21.261637357094035]
  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.
  arXiv  Detail & Related papers  (2024-04-22T22:04:16Z)
• Class-Incremental Few-Shot Event Detection [68.66116956283575]
  This paper proposes a new task, called class-incremental few-shot event detection. This task faces two problems, i.e., old knowledge forgetting and new class overfitting. To solve these problems, this paper presents a novel knowledge distillation and prompt learning based method, called Prompt-KD.
  arXiv  Detail & Related papers  (2024-04-02T09:31:14Z)
• Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt [58.880105981772324]
  We propose a novel framework named Attention-aware Self-adaptive Prompt (ASP) ASP encourages task-invariant prompts to capture shared knowledge by reducing specific information from the attention aspect. In summary, ASP prevents overfitting on base task and does not require enormous data in few-shot incremental tasks.
  arXiv  Detail & Related papers  (2024-03-14T20:34:53Z)
• INCPrompt: Task-Aware incremental Prompting for Rehearsal-Free Class-incremental Learning [36.506275240271925]
  INCPrompt is an innovative continual learning solution that effectively addresses catastrophic forgetting. Our comprehensive evaluation across multiple continual learning benchmarks demonstrates INCPrompt's superiority over existing algorithms.
  arXiv  Detail & Related papers  (2024-01-22T02:59:27Z)
• Online Continual Learning via the Knowledge Invariant and Spread-out Properties [4.109784267309124]
  Key challenge in continual learning is catastrophic forgetting. We propose a new method, named Online Continual Learning via the Knowledge Invariant and Spread-out Properties (OCLKISP) We empirically evaluate our proposed method on four popular benchmarks for continual learning: Split CIFAR 100, Split SVHN, Split CUB200 and Split Tiny-Image-Net.
  arXiv  Detail & Related papers  (2023-02-02T04:03:38Z)
• Learning with Recoverable Forgetting [77.56338597012927]
  Learning wIth Recoverable Forgetting explicitly handles the task- or sample-specific knowledge removal and recovery. Specifically, LIRF brings in two innovative schemes, namely knowledge deposit and withdrawal. We conduct experiments on several datasets, and demonstrate that the proposed LIRF strategy yields encouraging results with gratifying generalization capability.
  arXiv  Detail & Related papers  (2022-07-17T16:42:31Z)
• 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)

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.