paper-with-me

홈 › Papers

LW2G: Learning Whether to Grow for Prompt-based Continual Learning

2024-09-27 · Qian Feng, Dawei Zhou, Hanbin Zhao, Chao Zhang, Hui Qian

Continual Learning (CL) aims to learn in non-stationary scenarios, progressively acquiring and maintaining knowledge from sequential tasks. Recent Prompt-based Continual Learning (PCL) has achieved remarkable performance with Pre-Trained Models (PTMs). These approaches grow a prompt sets pool by adding a new set of prompts when learning each new task (\emph{prompt learning}) and adopt a matching mechanism to select the correct set for each testing sample (\emph{prompt retrieval}). Previous studies focus on the latter stage by improving the matching mechanism to enhance Prompt Retrieval Accuracy (PRA). To promote cross-task knowledge facilitation and form an effective and efficient prompt sets pool, we propose a plug-in module in the former stage to \textbf{Learn Whether to Grow (LW2G)} based on the disparities between tasks. Specifically, a shared set of prompts is utilized when several tasks share certain commonalities, and a new set is added when there are significant differences between the new task and previous 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 by surgically modifying the original gradient onto the orthogonal complement of the old feature space. With HFC, an automated scheme Dynamic Growing Approach adaptively learns whether to grow with a dynamic threshold. Furthermore, we design a gradient-based constraint to ensure the consistency between the updating prompts and pre-trained knowledge, and a prompts weights reusing strategy to enhance forward transfer. Extensive experiments show the effectiveness of our method. The source codes are available at \url{https://github.com/RAIAN08/LW2G}.

📄 PDF Abstract BibTeX arXiv:2409.18860

Code (1)

raian08/lw2g 공식 구현 pytorch

Tasks

Continual LearningPrompt LearningRetrieval

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음

Similar Papers 제목 키워드 기반

ModalPrompt:Dual-Modality Guided Prompt for Continual Learning of Large Multimodal Models

2024-10-08 · Fanhu Zeng, Fei Zhu, Haiyang Guo, Xu-Yao Zhang 외

Large Multimodal Models (LMMs) exhibit remarkable multi-tasking ability by learning mixed datasets jointly. However, novel tasks would be encountered sequentially in dynamic world, and continually fine-tuning LMMs often …

Continual LearningPrompt LearningTransfer Learning

PromptFusion: Decoupling Stability and Plasticity for Continual Learning

2023-03-13 · Haoran Chen, Zuxuan Wu, Xintong Han, Menglin Jia 외

Current research on continual learning mainly focuses on relieving catastrophic forgetting, and most of their success is at the cost of limiting the performance of newly incoming tasks. Such a trade-off is referred to as…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning

GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning

2025-07-19 · Anushka Tiwari, Sayantan Pal, Rohini K. Srihari, Kaiyi Ji arxiv

Prompt-based continual learning (CL) offers a parameter-efficient way to adapt large language models (LLMs) across task sequences. However, existing methods often rely on task-aware inference and maintain an expanding se…

Continual Learning

ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement

2024-12-25 · Zhefan Rao, Liya Ji, Yazhou Xing, Runtao Liu 외

Text-to-video (T2V) generation has gained significant attention recently. However, the costs of training a T2V model from scratch remain persistently high, and there is considerable room for improving the generation perf…

Understanding Generalization and Forgetting in In-Context Continual Learning

2026-05-27 · Guangyu Li, Meng Ding, Lijie Hu arxiv

In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study…

Continual Learning