AI RESEARCH
SR$^2$-LoRA: Self-Rectifying Inter-layer Relations in Low-Rank Adaptation for Class-Incremental Learning
arXiv CS.LG
•
ArXi:2605.07420v1 Announce Type: new Pre-trained models with parameter-efficient fine-tuning (PEFT) have nstrated promising potential for class-incremental learning (CIL), yet catastrophic forgetting still persists when adapting models to new tasks. In this paper, we present a novel perspective on catastrophic forgetting through the analysis of inter-layer relation drift, i.e., the progressive disruption of relationships among layer-wise representations during the learning of new tasks.