Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks

• Main Authors: Ke, Zixuan, Liu, Bing, Xiong, Wenhan, Celikyilmaz, Asli, Li, Haoran
• Format: Journal Article
• Language: English
• Published: 13.10.2023
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Computation and Language; Computer Science - Learning; Computer Science - Neural and Evolutionary Computing
• DOI: 10.48550/arxiv.2310.09436

EMNLP 2023 (findings) 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.