Adapters present a promising solution to the catastrophic forgetting problem in continual learning. However, training independent Adapter modules for every new task misses an opportunity for cross-task knowledge transfer. We propose Improvise to Initialize (I2I), a continual learning algorithm that initializes Adapters for incoming tasks by distilling knowledge from previously-learned tasks' Adapters. We evaluate I2I on CLiMB, a multimodal continual learning benchmark, by conducting experiments on sequences of visual question answering tasks. Adapters trained with I2I consistently achieve better task accuracy than independently-trained Adapters, demonstrating that our algorithm facilitates knowledge transfer between task Adapters. I2I also results in better cross-task knowledge transfer than the state-of-the-art AdapterFusion without incurring the associated parametric cost.
翻译:Adapters 提供了一种解决持续学习中灾难性遗忘问题的有前途的解决方案。然而,为每个新任务训练独立的 Adapter 模块会错过跨任务的知识转移机会。我们提出了 Improvise to Initialize (I2I),这是一种持续学习算法,可以通过提炼先前学习的任务 Adapter 的知识,为即将到来的任务初始化 Adapter。我们在 CLiMB 上评估了 I2I,这是一个多模态的持续学习基准测试,并通过对一系列视觉问答任务进行实验来进行评估。使用 I2I 训练的 Adapters 始终比独立训练的 Adapters 实现更好的任务准确性,证明了我们的算法有助于任务 Adapter 之间的知识转移。I2I 还实现了比现有技术 AdapterFusion 更好的跨任务知识转移,而不会造成相关参数成本。