InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning

arXiv:2404.00228v1 Announce Type: new
Abstract: Continual learning requires the model to learn multiple tasks sequentially. In continual learning, the model should possess the ability to maintain its performance on old tasks (stability) and the ability to adapt to new tasks continuously (plasticity). Recently, parameter-efficient fine-tuning (PEFT), which involves freezing a pre-trained model and injecting a small number of learnable parameters to adapt to downstream tasks, has gained increasing popularity in continual learning. Although existing continual learning methods based on PEFT …

abstract adapt arxiv continual cs.ai cs.cv cs.lg fine-tuning free interference learn low low-rank adaptation multiple peft performance pre-trained model stability tasks type