Thanks for your impressive work. There is still one thing that I can't figure out. According to the setting of continual learning, when learning on the current task, the data from previous tasks is unavailable. My question is, how do you make sure that the G(eneral)-Prompt learned on the current task also works for previous tasks? How do you deal with the forgetting problem of the G(eneral)-Prompt itself?
Thanks for your impressive work. There is still one thing that I can't figure out. According to the setting of continual learning, when learning on the current task, the data from previous tasks is unavailable. My question is, how do you make sure that the G(eneral)-Prompt learned on the current task also works for previous tasks? How do you deal with the forgetting problem of the G(eneral)-Prompt itself?