提出MAGIC Net，用可学习掩码实现在线回溯记忆，缓解流数据中的概念漂移与遗忘。
Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence
- 引入可学习掩码机制，让网络在不更新权重的情况下回看历史知识
- 在真实和合成数据流上验证，显著降低遗忘率并控制内存增长
- 适合需要持续学习且资源受限的实时场景，如智能监控、金融风控
概念漂移、时间依赖性和灾难性遗忘是流数据学习面临的主要挑战。尽管流机器学习和持续学习（CL）分别应对这些问题，但近期的流持续学习（SCL）尝试将二者统一。本文提出MAGIC Net，一种新颖的SCL方法，融合了受持续学习启发的架构策略与循环神经网络，以应对时间依赖性。MAGIC Net能够持续学习，通过在冻结权重上应用可学习掩码来回顾过往知识，并在必要时扩展架构。所有操作均在线完成，确保始终可进行推理。在合成与真实数据流上的实验表明，该方法提升了对新概念的适应能力，限制了内存使用，并减轻了遗忘问题。
原文摘要 · Abstract (English)
Concept drift, temporal dependence, and catastrophic forgetting represent major challenges when learning from data streams. While Streaming Machine Learning and Continual Learning (CL) address these issues separately, recent efforts in Streaming Continual Learning (SCL) aim to unify them. In this work, we introduce MAGIC Net, a novel SCL approach that integrates CL-inspired architectural strategies with recurrent neural networks to tame temporal dependence. MAGIC Net continuously learns, looks back at past knowledge by applying learnable masks over frozen weights, and expands its architecture when necessary. It performs all operations online, ensuring inference availability at all times. Experiments on synthetic and real-world streams show that it improves adaptation to new concepts, limits memory usage, and mitigates forgetting.
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。