Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data. This need can be adequately addressed by continual learning (CL), which allows systems to gradually acquire knowledge without incurring the prohibitive costs of retraining them from scratch. Most research on continual learning focuses on classification problems, while very few studies address regression tasks. We propose the first prototype-based generative replay framework designed for online task-free continual regression. Our approach defines an adaptive output-space discretization model, enabling prototype-based generative replay for continual regression without storing raw data. Evidence obtained from several benchmark datasets shows that our framework reduces forgetting and provides more stable performance than other state-of-the-art solutions.

翻译：在工业4.0等动态环境中，数据流很少是静态的。相反，它们不断变化，使得传统的离线模型迅速过时，除非这些模型能够快速适应新数据。持续学习（CL）能够充分应对这一需求，它使系统能够逐步获取知识，而无需承担从头重新训练的高昂成本。目前大多数持续学习研究集中于分类问题，而针对回归任务的研究极少。本文提出了首个基于原型的生成式回放框架，专为在线无任务持续回归而设计。我们的方法定义了一种自适应输出空间离散化模型，使得无需存储原始数据即可实现基于原型的生成式回放，以支持持续回归。在多个基准数据集上获得的实验证据表明，相较于其他先进解决方案，我们的框架能够有效减少灾难性遗忘，并提供更稳定的性能表现。