Ho Stella, Liu Ming, Du Lan, Gao Longxiang, Xiang Yong
IEEE Trans Neural Netw Learn Syst. 2024 Aug;35(8):10973-10983. doi: 10.1109/TNNLS.2023.3246049. Epub 2024 Aug 5.
Continual learning (CL) is a machine learning paradigm that accumulates knowledge while learning sequentially. The main challenge in CL is catastrophic forgetting of previously seen tasks, which occurs due to shifts in the probability distribution. To retain knowledge, existing CL models often save some past examples and revisit them while learning new tasks. As a result, the size of saved samples dramatically increases as more samples are seen. To address this issue, we introduce an efficient CL method by storing only a few samples to achieve good performance. Specifically, we propose a dynamic prototype-guided memory replay (PMR) module, where synthetic prototypes serve as knowledge representations and guide the sample selection for memory replay. This module is integrated into an online meta-learning (OML) model for efficient knowledge transfer. We conduct extensive experiments on the CL benchmark text classification datasets and examine the effect of training set order on the performance of CL models. The experimental results demonstrate the superiority our approach in terms of accuracy and efficiency.
持续学习（CL）是一种机器学习范式，它在顺序学习的同时积累知识。CL中的主要挑战是对先前见过的任务的灾难性遗忘，这是由于概率分布的变化而发生的。为了保留知识，现有的CL模型通常会保存一些过去的示例，并在学习新任务时重新审视它们。结果，随着看到的样本越来越多，保存样本的大小会急剧增加。为了解决这个问题，我们通过只存储少量样本引入了一种高效的CL方法，以实现良好的性能。具体来说，我们提出了一个动态原型引导的记忆重放（PMR）模块，其中合成原型作为知识表示，并指导用于记忆重放的样本选择。该模块被集成到一个在线元学习（OML）模型中，以实现高效的知识转移。我们在CL基准文本分类数据集上进行了广泛的实验，并研究了训练集顺序对CL模型性能的影响。实验结果证明了我们的方法在准确性和效率方面的优越性。
