paper-with-me

Papers

A Unified Continual Learning Framework with General Parameter-Efficient Tuning

2023-03-17 · ICCV 2023 1 · Qiankun Gao, Chen Zhao, Yifan Sun, Teng Xi, Gang Zhang, Bernard Ghanem, Jian Zhang

The "pre-training $\rightarrow$ downstream adaptation" presents both new opportunities and challenges for Continual Learning (CL). Although the recent state-of-the-art in CL is achieved through Parameter-Efficient-Tuning (PET) adaptation paradigm, only prompt has been explored, limiting its application to Transformers only. In this paper, we position prompting as one instantiation of PET, and propose a unified CL framework with general PET, dubbed as Learning-Accumulation-Ensemble (LAE). PET, e.g., using Adapter, LoRA, or Prefix, can adapt a pre-trained model to downstream tasks with fewer parameters and resources. Given a PET method, our LAE framework incorporates it for CL with three novel designs. 1) Learning: the pre-trained model adapts to the new task by tuning an online PET module, along with our adaptation speed calibration to align different PET modules, 2) Accumulation: the task-specific knowledge learned by the online PET module is accumulated into an offline PET module through momentum update, 3) Ensemble: During inference, we respectively construct two experts with online/offline PET modules (which are favored by the novel/historical tasks) for prediction ensemble. We show that LAE is compatible with a battery of PET methods and gains strong CL capability. For example, LAE with Adaptor PET surpasses the prior state-of-the-art by 1.3% and 3.6% in last-incremental accuracy on CIFAR100 and ImageNet-R datasets, respectively. Code is available at \url{https://github.com/gqk/LAE}.

📄 PDF Abstract BibTeX arXiv:2303.10070

Code (1)

gqk/lae 공식 구현 pytorch

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Adapter 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Gradient Projection For Continual Parameter-Efficient Tuning

2024-05-22 · Jingyang Qiao, Zhizhong Zhang, Xin Tan, Yanyun Qu 외

Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new c…

Continual LearningHallucinationZero-shot Generalization

Split-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning

2026-01-24 · Fatema Siddika, Md Anwar Hossen, Tanwi Mallick, Ali Jannesari arxiv

Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typicall…

parameter-efficient fine-tuningContinual Learning

Continual Gradient Low-Rank Projection Fine-Tuning for LLMs

2025-07-03 · Chenxu Wang, Yilin Lyu, Zicheng Sun, Liping Jing

Continual fine-tuning of Large Language Models (LLMs) is hampered by the trade-off between efficiency and expressiveness. Low-Rank Adaptation (LoRA) offers efficiency but constrains the model's ability to learn new tasks…

Continual Learning

Efficient Online Continual Foundation Model Fine-Tuning for Predictive Process Monitoring

2026-08-28 · Sjoerd van Straten, Marwan Hassani arxiv

Predictive Process Monitoring (PPM) models are increasingly deployed in dynamic environments where concept drift causes the underlying process distribution to shift over time. While recent work has moved toward online co…

Continual Learning

Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer

2024-03-29 · CVPR 2024 1 · Yuwen Tan, Qinhao Zhou, Xiang Xiang, Ke Wang 외

Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this p…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning