paper-with-me

Papers

P2DT: Mitigating Forgetting in task-incremental Learning with progressive prompt Decision Transformer

2024-01-22 · Zhiyuan Wang, Xiaoyang Qu, Jing Xiao, Bokui Chen, Jianzong Wang

Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive Prompt Decision Transformer (P2DT). This method enhances a transformer-based model by dynamically appending decision tokens during new task training, thus fostering task-specific policies. Our approach mitigates forgetting in continual and offline reinforcement learning scenarios. Moreover, P2DT leverages trajectories collected via traditional reinforcement learning from all tasks and generates new task-specific tokens during training, thereby retaining knowledge from previous studies. Preliminary results demonstrate that our model effectively alleviates catastrophic forgetting and scales well with increasing task environments.

📄 PDF Abstract BibTeX arXiv:2401.11666

Code (0)

등록된 구현이 없습니다.

Tasks

Incremental Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

INCPrompt: Task-Aware incremental Prompting for Rehearsal-Free Class-incremental Learning

2024-01-22 · Zhiyuan Wang, Xiaoyang Qu, Jing Xiao, Bokui Chen 외

This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptive key-learner and task-aware prompts tha…

class-incremental learningClass Incremental LearningContinual LearningGeneral Knowledge+1

Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt

2024-03-14 · Chenxi Liu, Zhenyi Wang, Tianyi Xiong, Ruibo Chen 외

Few-Shot Class-Incremental Learning (FSCIL) models aim to incrementally learn new classes with scarce samples while preserving knowledge of old ones. Existing FSCIL methods usually fine-tune the entire backbone, leading …

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning

CASP: Few-Shot Class-Incremental Learning with CLS Token Attention Steering Prompts

2026-01-23 · Shuai Huang, Xuhan Lin, Yuwu Lu arxiv

Few-shot class-incremental learning (FSCIL) presents a core challenge in continual learning, requiring models to rapidly adapt to new classes with very limited samples while mitigating catastrophic forgetting. Recent pro…

Few-Shot Class-Incremental LearningContinual Learning

Rehearsal-free Federated Domain-incremental Learning

2024-05-22 · Rui Sun, Haoran Duan, Jiahua Dong, Varun Ojha 외

We introduce a rehearsal-free federated domain incremental learning framework, RefFiL, based on a global prompt-sharing paradigm to alleviate catastrophic forgetting challenges in federated domain-incremental learning, w…

Contrastive LearningFederated LearningIncremental Learning

PAL: Prompting Analytic Learning with Missing Modality for Multi-Modal Class-Incremental Learning

2025-01-16 · Xianghu Yue, Yiming Chen, Xueyi Zhang, Xiaoxue Gao 외

Multi-modal class-incremental learning (MMCIL) seeks to leverage multi-modal data, such as audio-visual and image-text pairs, thereby enabling models to learn continuously across a sequence of tasks while mitigating forg…

class-incremental learningClass Incremental LearningExemplar-FreeIncremental Learning