paper-with-me

홈 › Papers

Investigating Forgetting in Pre-Trained Representations Through Continual Learning

2023-05-10 · Yun Luo, Zhen Yang, Xuefeng Bai, Fandong Meng, Jie zhou, Yue Zhang

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.

📄 PDF Abstract BibTeX arXiv:2305.05968

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningGeneral Knowledge

Similar Papers 제목 키워드 기반

Probing Representation Forgetting in Supervised and Unsupervised Continual Learning

2022-03-24 · CVPR 2022 1 · MohammadReza Davari, Nader Asadi, Sudhir Mudur, Rahaf Aljundi 외

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 Learning

Effect of scale on catastrophic forgetting in neural networks

2021-09-29 · ICLR 2022 4 · Vinay Venkatesh Ramasesh, Aitor Lewkowycz, Ethan Dyer

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 Learning

Meta-Learning Representations for Continual Learning

2019-05-29 · NeurIPS 2019 12 · Khurram Javed, Martha White

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-Learning

The Art of Not Forgetting A Local Learning Architecture for Continual Learning

2026-07-29 · Ashmith Atmuri, Yashaswini Rao Bhogarajula arxiv

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 Learning

Why Do Neural Networks Forget: A Study of Collapse in Continual Learning

2026-03-04 · Yunqin Zhu, Jun Jin arxiv

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