Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks
Zixuan Ke, Bing Liu, Wenhan Xiong, Asli Celikyilmaz, Haoran Li
Abstract
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 sub-network 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.
BibTeX
@inproceedings{
ke2023subnetwork,
title={Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks},
author={Zixuan Ke and Bing Liu and Wenhan Xiong and Asli Celikyilmaz and Haoran Li},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=3JBKnkUACW}
}