A Unified Continual Learning Framework with General Parameter-Efficient Tuning
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}.
Code (1)
Tasks
Continual LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Gradient Projection For Continual Parameter-Efficient Tuning
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 GeneralizationSplit-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning
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 LearningContinual Gradient Low-Rank Projection Fine-Tuning for LLMs
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 LearningEfficient Online Continual Foundation Model Fine-Tuning for Predictive Process Monitoring
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 LearningSemantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
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