Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks
This addresses the challenge of continual learning for heterogeneous tasks, which is incremental as it builds on prior work focused on similar tasks.
The paper tackles the problem of catastrophic forgetting and limited knowledge transfer in continual learning for mixed tasks by proposing a method that discovers subnetworks for each task and uses soft-masking to preserve and leverage past knowledge. Experiments show it consistently outperforms baselines across classification, generation, and information extraction tasks.
Continual learning (CL) has two main objectives: preventing catastrophic forgetting (CF) and encouraging knowledge transfer (KT). The existing literature mainly focused on overcoming CF. Some work has also been done on KT when the tasks are similar. To our knowledge, only one method has been proposed to learn a sequence of mixed tasks. However, these techniques still suffer from CF and/or limited KT. This paper proposes a new CL method to achieve both. It overcomes CF by isolating the knowledge of each task via discovering a subnetwork for it. A soft-masking mechanism is also proposed to preserve the previous knowledge and to enable the new task to leverage the past knowledge to achieve KT. Experiments using classification, generation, information extraction, and their mixture (i.e., heterogeneous tasks) show that the proposed method consistently outperforms strong baselines.