Investigating Forgetting in Pre-Trained Representations Through Continual Learning
Representation forgetting refers to the drift of contextualized representations during continual training. Intuitively, the representation forgetting can influence the general knowledge stored in pre-trained language models (LMs), but the concrete effect is still unclear. In this paper, we study the effect of representation forgetting on the generality of pre-trained language models, i.e. the potential capability for tackling future downstream tasks. Specifically, we design three metrics, including overall generality destruction (GD), syntactic knowledge forgetting (SynF), and semantic knowledge forgetting (SemF), to measure the evolution of general knowledge in continual learning. With extensive experiments, we find that the generality is destructed in various pre-trained LMs, and syntactic and semantic knowledge is forgotten through continual learning. Based on our experiments and analysis, we further get two insights into alleviating general knowledge forgetting: 1) training on general linguistic tasks at first can mitigate general knowledge forgetting; 2) the hybrid continual learning method can mitigate the generality destruction and maintain more general knowledge compared with those only considering rehearsal or regularization.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningGeneral KnowledgeSimilar Papers 제목 키워드 기반
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning
Continual Learning research typically focuses on tackling the phenomenon of catastrophic forgetting in neural networks. Catastrophic forgetting is associated with an abrupt loss of knowledge previously learned by a model…
Continual LearningContrastive LearningEffect of scale on catastrophic forgetting in neural networks
Catastrophic forgetting presents a challenge in developing deep learning models capable of continual learning, i.e. learning tasks sequentially. Recently, both computer vision and natural-language processing have witness…
Continual LearningMeta-Learning Representations for Continual Learning
A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguabl…
Continual LearningMeta-LearningThe Art of Not Forgetting A Local Learning Architecture for Continual Learning
We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre?sents inputs as sparse relational codes, stores them in a two-tier competitive memory, and learns through local updates without …
Continual LearningWhy Do Neural Networks Forget: A Study of Collapse in Continual Learning
Catastrophic forgetting is a major problem in continual learning, and lots of approaches arise to reduce it. However, most of them are evaluated through task accuracy, which ignores the internal model structure. Recent r…
Continual Learning