非稳态回归的持续学习：通过高效记忆回放
Continual Learning for non-stationary regression via Memory-Efficient Replay
AI总结：
本文提出了一种基于原型的生成回放框架，用于在线任务无关的持续回归，通过自适应输出空间离散化模型减少遗忘并提高稳定性。
摘要：
在工业4.0等动态环境中，数据流很少静态。相反，它们不断变化，使传统离线模型过时，除非能够快速适应新数据。这一需求可以通过持续学习（CL）来充分满足，允许系统逐步获取知识，而无需承担重新训练的高昂成本。大多数持续学习研究集中在分类问题上，而非常少有研究涉及回归任务。我们提出了第一个基于原型的生成回放框架，专门用于在线任务无关的持续回归。我们的方法定义了一个自适应的输出空间离散化模型，使原型基于的生成回放能够用于持续回归，而无需存储原始数据。从几个基准数据集获得的证据表明，我们的框架比其他最先进的解决方案减少了遗忘并提供了更稳定的性能。
英文摘要：
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 Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data.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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
