用状态记忆回放缓解流式学习中的灾难性遗忘，提升多任务场景表现。
Mitigating Catastrophic Forgetting in Streaming Generative and Predictive Learning via Stateful Replay
- 设计基于梯度对齐的状态记忆回放机制，统一处理生成与预测任务。
- 在异构多任务流上，遗忘率降低2到3倍；时间序列流上效果相当。
- 适合资源受限的实时模型更新场景，可作为简单可靠的基准方案。
许多部署的学习系统需在内存受限条件下对流式数据持续更新模型。默认的顺序微调策略虽与架构无关，但在后续阶段对应不同子群体或任务时，常出现灾难性遗忘。有限缓冲区的回放是一种简单替代方案，但其在生成与预测目标下的行为尚不明确。本文首次统一研究了状态记忆回放在流式自编码、时间序列预测和分类任务中的表现。我们将顺序微调与回放均视为理想联合目标的随机梯度方法，通过梯度对齐分析揭示何时混合当前与历史样本能减少遗忘。随后，在基于旋转MNIST、ElectricityLoadDiagrams 2011-2014和航班延误数据构建的六个流式场景中，使用相同训练预算与三组种子进行评估。在异构多任务流上，回放将平均遗忘率降低2至3倍；而在温和的时间驱动流上，两种方法表现相近。结果表明，状态记忆回放是流式环境持续学习中一种强大且简单的基线方法。
原文摘要 · Abstract (English)
Many deployed learning systems must update models on streaming data under memory constraints. The default strategy, sequential fine-tuning on each new phase, is architecture-agnostic but often suffers catastrophic forgetting when later phases correspond to different sub-populations or tasks. Replay with a finite buffer is a simple alternative, yet its behaviour across generative and predictive objectives is not well understood. We present a unified study of stateful replay for streaming autoencoding, time series forecasting, and classification. We view both sequential fine-tuning and replay as stochastic gradient methods for an ideal joint objective, and use a gradient alignment analysis to show when mixing current and historical samples should reduce forgetting. We then evaluate a single replay mechanism on six streaming scenarios built from Rotated MNIST, ElectricityLoadDiagrams 2011-2014, and Airlines delay data, using matched training budgets and three seeds. On heterogeneous multi task streams, replay reduces average forgetting by a factor of two to three, while on benign time based streams both methods perform similarly. These results position stateful replay as a strong and simple baseline for continual learning in streaming environments.
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。