arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.08347cs.LGcs.AI
收藏

用于建模长期时间依赖性的小批量学习策略:环境应用研究

Mini-Batch Learning Strategies for modeling long term temporal dependencies: A study in environmental applications

University of Minnesota(明尼苏达大学);University of Pittsburgh(匹兹堡大学);Pennsylvania State University(宾夕法尼亚州立大学)

Shaoming Xu, Ankush Khandelwal, Xiang Li, Xiaowei Jia, Licheng Liu, Jared Willard, Rahul Ghosh, Kelly Cutler, Michael Steinbach, Christopher Duffy, John Nieber, Vipin Kumar

摘要:

在许多环境应用中,经常使用递归神经网络(RNN)来建模具有长时间依赖性的物理变量。然而,由于小批量训练,不考虑批内(批内)以及批之间(批间)的训练段之间的时间关系,这可能导致有限的性能。有状态RNN旨在通过在批处理之间传递隐藏状态来解决这个问题。由于有状态RNN忽略了批内时间依赖性,因此在训练稳定性和捕获时间依赖性之间存在权衡。在本文中,我们提供了不同的有状态RNN建模策略的定量比较,并提出了两种策略,以加强批内和批间的时间依赖性。首先,我们通过将一个批次定义为一组按时间排序的训练片段来扩展有状态RNN,这使得批次内能够共享时间信息。虽然这种方法显着提高了性能,但由于高度连续的训练,它导致了更大的训练时间。为了解决这个问题,我们进一步提出了一种新的策略,该策略从训练段开始之前的时间步开始,用目标变量的初始值来增加训练段。换句话说,我们提供目标变量的初始值作为额外的输入,这样网络就可以专注于学习相对于初始值的变化。通过使用这种策略,样本可以以任何顺序传递(小批量训练),这大大减少了训练时间,同时保持了性能。在演示我们的水文建模方法时,我们观察到,当这些方法应用于值变化较慢的状态变量(如土壤水和积雪)而不是持续移动的通量变量(如径流)时,预测准确性会获得最显著的收益。

英文摘要:

In many environmental applications, recurrent neural networks (RNNs) are often used to model physical variables with long temporal dependencies. However, due to mini-batch training, temporal relationships between training segments within the batch (intra-batch) as well as between batches (inter-batch) are not considered, which can lead to limited performance. Stateful RNNs aim to address this issue by passing hidden states between batches. Since Stateful RNNs ignore intra-batch temporal dependency, there exists a trade-off between training stability and capturing temporal dependency. In this paper, we provide a quantitative comparison of different Stateful RNN modeling strategies, and propose two strategies to enforce both intra- and inter-batch temporal dependency. First, we extend Stateful RNNs by defining a batch as a temporally ordered set of training segments, which enables intra-batch sharing of temporal information. While this approach significantly improves the performance, it leads to much larger training times due to highly sequential training. To address this issue, we further propose a new strategy which augments a training segment with an initial value of the target variable from the timestep right before the starting of the training segment. In other words, we provide an initial value of the target variable as additional input so that the network can focus on learning changes relative to that initial value. By using this strategy, samples can be passed in any order (mini-batch training) which significantly reduces the training time while maintaining the performance. In demonstrating our approach in hydrological modeling, we observe that the most significant gains in predictive accuracy occur when these methods are applied to state variables whose values change more slowly, such as soil water and snowpack, rather than continuously moving flux variables such as streamflow.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑