Sub-network Discovery and Soft-masking for Continual Learning of Mixed 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.
Code (1)
Tasks
Continual LearningTransfer LearningSimilar Papers 제목 키워드 기반
Linguistic Entity Masking to Improve Cross-Lingual Representation of Multilingual Language Models for Low-Resource Languages
Multilingual Pre-trained Language models (multiPLMs), trained on the Masked Language Modelling (MLM) objective are commonly being used for cross-lingual tasks such as bitext mining. However, the performance of these mode…
Language ModellingSentiment AnalysisRevisiting Softmax Masking: Stop Gradient for Enhancing Stability in Replay-based Continual Learning
In replay-based methods for continual learning, replaying input samples in episodic memory has shown its effectiveness in alleviating catastrophic forgetting. However, the potential key factor of cross-entropy loss with …
Continual LearningIncremental LearningParameter-Level Soft-Masking for Continual Learning
Existing research on task incremental learning in continual learning has primarily focused on preventing catastrophic forgetting (CF). Although several techniques have achieved learning with no CF, they attain it by lett…
Continual LearningIncremental LearningTransfer LearningOffline Multi-agent Continual Cooperation via Skill Partition and Reuse
Extracting skills from multi-agent offline dataset improves learning efficiency via sharing task-invariant coordination skills among tasks. In settings where tasks occur sequentially and the space of skills grows exponen…
Soft-TransFormers for Continual Learning
Inspired by Well-initialized Lottery Ticket Hypothesis (WLTH), which provides suboptimal fine-tuning solutions, we propose a novel fully fine-tuned continual learning (CL) method referred to as Soft-TransFormers (Soft-TF…
class-incremental learningClass Incremental LearningContinual LearningIncremental Learning