提出首个无需存储原始数据的在线回归持续学习框架。
Continual Learning for non-stationary regression via Memory-Efficient Replay
- 用自适应输出空间离散化构建原型生成回放机制
- 在多个基准数据集上显著降低遗忘率并稳定性能
- 适合工业4.0等动态环境中的实时回归任务
在工业4.0等动态环境中，数据流通常非静态，持续变化，导致传统离线模型快速过时。持续学习（CL）可让系统在不从头训练的前提下逐步适应新数据，有效应对这一挑战。尽管多数持续学习研究聚焦分类任务，针对回归任务的研究仍十分有限。本文提出首个面向在线、无任务持续回归的基于原型的生成式回放框架。该方法引入自适应输出空间离散化模型，实现无需存储原始数据的原型生成回放。在多个基准数据集上的实验表明，该框架能显著减少遗忘现象，并提供更稳定的性能表现，优于现有主流方法。
原文摘要 · Abstract (English)
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 Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data.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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。