Bi-directional online transfer learning: a framework
Bi-directional online transfer learning: a framework
复制标题
DOI：
10.1007/s12243-020-00776-1
复制
发表时间：
2020-10
影响因子：
1.9
通讯作者：
Helen McKay;N. Griffiths;Phillip Taylor;T. Damoulas;Zhou Xu
中科院分区：
文献类型：
--
作者：
Helen McKay;N. Griffiths;Phillip Taylor;T. Damoulas;Zhou Xu
迁移学习使用在源域中学到的知识来帮助在目标域中进行预测。当源域和目标域在线时，它们很容易受到概念漂移的影响，这可能会改变它们之间的知识映射。在线环境中的漂移可以在每个领域提供额外的信息，从而需要持续从源到目标的知识转移，反之亦然。为了解决这个问题，我们引入了双向在线迁移学习（BOTL）框架，该框架使用在每个在线领域学到的知识来帮助在其他领域进行预测。我们引入了 BOTL 的两种变体，它们结合了模型剔除，以最大限度地减少具有大量模型传输的框架中的负传输。我们考虑了 BOTL 的理论损失，这表明 BOTL 实现的损失不比底层概念漂移检测算法差。我们使用两种现有的概念漂移检测算法来评估 BOTL：RePro 和 ADWIN。此外，我们提出了一种概念漂移检测算法，即带有主动漂移检测的自适应窗口（AWPro），它减少了 BOTL 的计算和通信需求。使用两个数据流生成器提供了经验结果：漂移超平面模拟器和智能家居供暖模拟器，以及通过车辆遥测预测碰撞时间 (TTC) 的真实世界数据。评估显示 BOTL 及其变体优于概念漂移检测策略和现有最先进的在线迁移学习技术。
Transfer learning uses knowledge learnt in source domains to aid predictions in a target domain. When source and target domains are online, they are susceptible to concept drift, which may alter the mapping of knowledge between them. Drifts in online environments can make additional information available in each domain, necessitating continuing knowledge transfer both from source to target and vice versa. To address this, we introduce the Bi-directional Online Transfer Learning (BOTL) framework, which uses knowledge learnt in each online domain to aid predictions in others. We introduce two variants of BOTL that incorporate model culling to minimise negative transfer in frameworks with high volumes of model transfer. We consider the theoretical loss of BOTL, which indicates that BOTL achieves a loss no worse than the underlying concept drift detection algorithm. We evaluate BOTL using two existing concept drift detection algorithms: RePro and ADWIN. Additionally, we present a concept drift detection algorithm, Adaptive Windowing with Proactive drift detection (AWPro), which reduces the computation and communication demands of BOTL. Empirical results are presented using two data stream generators: the drifting hyperplane emulator and the smart home heating simulator, and real-world data predicting Time To Collision (TTC) from vehicle telemetry. The evaluation shows BOTL and its variants outperform the concept drift detection strategies and the existing state-of-the-art online transfer learning technique.