Parameter Efficient Continual Learning with Dynamic Low-Rank Adaptation
Catastrophic forgetting has remained a critical challenge for deep neural networks in Continual Learning (CL) as it undermines consolidated knowledge when learning new tasks. Parameter efficient fine tuning CL techniques are gaining traction for their effectiveness in addressing catastrophic forgetting with a lightweight training schedule while avoiding degradation of consolidated knowledge in pre-trained models. However, low rank adapters (LoRA) in these approaches are highly sensitive to rank selection which can lead to sub-optimal resource allocation and performance. To this end, we introduce PEARL, a rehearsal-free CL framework that entails dynamic rank allocation for LoRA components during CL training. Specifically, PEARL leverages reference task weights and adaptively determines the rank of task-specific LoRA components based on the current tasks' proximity to reference task weights in parameter space. To demonstrate the versatility of PEARL, we evaluate it across three vision architectures (ResNet, Separable Convolutional Network and Vision Transformer) and a multitude of CL scenarios, and show that PEARL outperforms all considered baselines by a large margin.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual Learningparameter-efficient fine-tuningSimilar Papers 제목 키워드 기반
C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models
Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision. Existing LoRA fine-tuning approaches excel in static envir…
Continual LearningViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
Since real-world machine systems are running in non-stationary environments, Continual Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually changing target domains. Recently, existin…
Test-time AdaptationMINGLE: Mixtures of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
Continual model merging integrates independently fine-tuned models sequentially without access to original training data, providing a scalable and efficient solution to continual learning. However, current methods still …
Continual LearningMixture-of-ExpertsTest-time AdaptationHyLoVQA: Dynamic Hypernetwork-Generated Low-Rank Adaptation for Continual Visual Question Answering
Continual Visual Question Answering (VQA) requires learning from non-stationary streams of visual inputs and questions while preserving past knowledge. Most prior methods adapt by updating a largely shared parameter set.…
Visual Question AnsweringDual Low-Rank Adaptation for Continual Learning with Pre-Trained Models
In the era of foundation models, we revisit continual learning~(CL), which aims to enable vision transformers (ViTs) to learn new tasks over time. However, as the scale of these models increases, catastrophic forgetting …
Continual Learningparameter-efficient fine-tuning