Meta-Learning Dynamics Forecasting Using Task Inference
Meta-Learning Dynamics Forecasting Using Task Inference
复制标题
DOI：
--
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
Rui Wang;R. Walters;Rose Yu
中科院分区：
文献类型：
--
作者：
Rui Wang;R. Walters;Rose Yu
目前用于动态预测的深度学习模型难以推广。它们只能在特定的领域进行预测，当应用于具有不同参数、外力或边界条件的系统时，它们会失败。我们提出了一种基于模型的元学习方法DYAD，该方法通过将不同的领域划分为不同的任务来实现跨领域的泛化。DYAD有两个部分：一个是编码器，它推断弱监督任务的时不变隐藏特征；另一个是预测器，它学习整个领域的共享动态。在推理过程中，编码器使用自适应实例归一化和自适应填充来适应和控制预测器。理论上，我们证明了这类过程的泛化误差与源域中任务的关联性以及源与目标之间的域差异有关。在实验上，我们证明了我们的模型在湍流和真实世界海洋数据预测任务上都优于最先进的方法。
Current deep learning models for dynamics forecasting struggle with generalization. They can only forecast in a specific domain and fail when applied to systems with different parameters, external forces, or boundary conditions. We propose a model-based meta-learning method called DyAd which can generalize across heterogeneous domains by partitioning them into different tasks. DyAd has two parts: an encoder which infers the time-invariant hidden features of the task with weak supervision, and a forecaster which learns the shared dynamics of the entire domain. The encoder adapts and controls the forecaster during inference using adaptive instance normalization and adaptive padding. Theoretically, we prove that the generalization error of such procedure is related to the task relatedness in the source domain, as well as the domain differences between source and target. Experimentally, we demonstrate that our model outperforms state-of-the-art approaches on both turbulent flow and real-world ocean data forecasting tasks.