Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning

• URL: http://arxiv.org/abs/2303.09447v3
• Date: Sun, 12 Nov 2023 21:28:47 GMT
• Title: Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning
• Authors: Zhuowei Li, Long Zhao, Zizhao Zhang, Han Zhang, Di Liu, Ting Liu, Dimitris N. Metaxas
• Abstract summary: Prototypes as representative class embeddings offer advantages in memory conservation and the mitigation of catastrophic forgetting. In this study, we introduce the Contrastive Prototypical Prompt ( CPP) approach. CPP achieves a significant 4% to 6% improvement over state-of-the-art methods.
• Score: 47.83442130744575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting. However, challenges related to semantic drift and prototype interference persist. In this study, we introduce the Contrastive Prototypical Prompt (CPP) approach. Through task-specific prompt-tuning, underpinned by a contrastive learning objective, we effectively address both aforementioned challenges. Our evaluations on four challenging class-incremental benchmarks reveal that CPP achieves a significant 4% to 6% improvement over state-of-the-art methods. Importantly, CPP operates without a rehearsal buffer and narrows the performance divergence between continual and offline joint-learning, suggesting an innovative scheme for Transformer-based continual learning systems.

Related papers

• Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning [9.712093262192733]
  We propose a simple yet effective method named DisCo to deal with class-incremental learning tasks. DisCo can be easily integrated into existing state-of-the-art class-incremental learning methods. Experimental results show that incorporating our method into various CIL methods achieves substantial performance improvements.
  arXiv  Detail & Related papers  (2024-12-31T03:02:20Z)
• Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation [69.60321475454843]
  We propose DPCPL, the first pre-training and prompt-tuning paradigm tailored for Multi-Behavior Sequential Recommendation. In the pre-training stage, we propose a novel Efficient Behavior Miner (EBM) to filter out the noise at multiple time scales. Subsequently, we propose to tune the pre-trained model in a highly efficient manner with the proposed Customized Prompt Learning (CPL) module.
  arXiv  Detail & Related papers  (2024-08-21T06:48:38Z)
• SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training [68.7896349660824]
  We present an in-depth analysis of the progressive overfitting problem from the lens of Seq FT. Considering that the overly fast representation learning and the biased classification layer constitute this particular problem, we introduce the advanced Slow Learner with Alignment (S++) framework. Our approach involves a Slow Learner to selectively reduce the learning rate of backbone parameters, and a Alignment to align the disjoint classification layers in a post-hoc fashion.
  arXiv  Detail & Related papers  (2024-08-15T17:50:07Z)
• Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation [14.25441464051506]
  We propose Contrastive Continual Learning via Importance Sampling (CCLIS) to preserve knowledge by recovering previous data distributions. We also present the Prototype-instance Relation Distillation (PRD) loss, a technique designed to maintain the relationship between prototypes and sample representations.
  arXiv  Detail & Related papers  (2024-03-07T15:47:52Z)
• Doubly Perturbed Task Free Continual Learning [21.68539590444844]
  Task Free online continual learning (TF-CL) is a challenging problem where the model incrementally learns tasks without explicit task information. We propose a novel TF-CL framework considering future samples and show that injecting adversarial perturbations on both input data and decision-making is effective.
  arXiv  Detail & Related papers  (2023-12-20T13:50:26Z)
• Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning [53.97273491846883]
  We propose DPE: an RL algorithm that blends offline sequence modeling and offline reinforcement learning with Double Policy Estimation. We validate our method in multiple tasks of OpenAI Gym with D4RL benchmarks.
  arXiv  Detail & Related papers  (2023-08-28T20:46:07Z)
• Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference [61.11137714507445]
  This paper focuses on the prevalent performance imbalance in the stages of incremental learning. We propose a stage-isolation based incremental learning framework. We evaluate the proposed method on four large benchmarks.
  arXiv  Detail & Related papers  (2022-11-29T06:57:48Z)
• CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning [30.676509834338884]
  Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. We propose prompting approaches as an alternative to data-rehearsal. We show that we outperform the current SOTA method DualPrompt on established benchmarks by as much as 4.5% in average final accuracy.
  arXiv  Detail & Related papers  (2022-11-23T18:57:11Z)
• Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint [31.094612936162754]
  Active learning is a promising alternative to alleviate the issue of high annotation cost in the computer vision tasks. We propose a novel hybrid approach to address this problem, where the instance-level uncertainty and diversity are jointly considered in a bottom-up manner.
  arXiv  Detail & Related papers  (2022-04-17T09:51:12Z)
• Incremental Prototype Prompt-tuning with Pre-trained Representation for Class Incremental Learning [4.717066668969749]
  Class incremental learning has attracted much attention, but most existing works still continually fine-tune the representation model. We take the pre-train-and-prompt-tuning paradigm to sequentially learn new visual concepts based on a fixed semantic rich pre-trained representation model. Our method consistently outperforms other state-of-the-art methods with a large margin.
  arXiv  Detail & Related papers  (2022-04-07T12:49:14Z)
• Transfer Heterogeneous Knowledge Among Peer-to-Peer Teammates: A Model Distillation Approach [55.83558520598304]
  We propose a brand new solution to reuse experiences and transfer value functions among multiple students via model distillation. We also describe how to design an efficient communication protocol to exploit heterogeneous knowledge. Our proposed framework, namely Learning and Teaching Categorical Reinforcement, shows promising performance on stabilizing and accelerating learning progress.
  arXiv  Detail & Related papers  (2020-02-06T11:31:04Z)

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.