AI RESEARCH

Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning

arXiv CS.LG

ArXi:2603.00191v2 Announce Type: replace Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuning (PEFT) method, has gained increasing attention in CL. Several LoRA-based CL methods reduce interference across tasks by separating their update spaces, typically building the new space from the estimated null space of past tasks.