Forgetting of task-specific knowledge in model merging-based continual learning

This paper investigates the linear merging of models in the context of continual learning (CL). Using controlled visual cues in computer vision experiments, we demonstrate that merging largely preserves or enhances shared knowledge, while unshared task-specific knowledge rapidly degrades. We further find that merging models from an incremental training process consistently outperforms merging models trained in parallel.