A Unified Continual Learning Framework with General Parameter-Efficient Tuning

By Qiankun Gao, Chen Zhao, Yifan Sun, Teng Xi, Gang Zhang, Bernard Ghanem, Jing Zhang. 2023

161 citations recorded by the source corpus.

The "pre-training → 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 https://github.com/gqk/LAE.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning (2024, methodology): “Apart from prompt tuning, LAE [21] proposes EMA-based model updating with online and offline models.”
Pre-trained Vision and Language Transformers are Few-Shot Incremental Learners (2024, background): “However, since prefix tuning has a limitation of updating B-Prompt as mentioned in [4, 5] which is the slow adaptation speed of learnable prompts, B-Prompt cannot properly learn domain-specific knowledge and can be ignored by the fine-tuned layers.”
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey (2024, background): “Therefore, similar to LLMs, PEFT widely implemented in various downstream tasks, such as dense prediction [25], continual learning [182], [53], deep metric learning [151].”
One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning (2023, methodology): “Recently, rehersal-free continual learning (CL) methods (Wang et al., 2022c;a;b; Gao et al., 2023) have gained interest because of their superior performance even without using previous samples.”