当前共找到 1 篇文献分享。
1.
张浩彬 (2022-08-09 15:58):
#paper 10.1145/3394486.3403118 Connecting the Dots_Multivariate Time Series Forecasting with Graph Neural Networks: KDD2020的文章,感觉最大创新就是可以自适应创建图-但是细读下来又感觉乏善可陈;总的来说,感觉是把时空一套的东西套到了多时间序列中。最后也证明了,这套框架虽然可以用于多序列问题,但是还是时空效果最好,这也是不难理解、 本文提出了交MTGNN的基于图神经网络的模型来处理多序列的预测问题。本文认为多序列预测主要解决两个问题,分别是(1)怎么自适应生成图;(2)怎么在训练中根性图。 挑战1:图结构需要学习;通过3个核心组件解决:(1)图学习层:基于数据自适应提取稀疏图邻接矩阵(2)图卷积层:解决变量间的空间以来关系,转为有向图设计,避免图卷积网络的过渡平滑;(3)时间卷积层:通过一维卷积捕获时间模式--可以发现多个时间模式以及长时间网络 挑战2:训练中不仅参数需要更新,图结构也需要更新(要在端到端学习中完成这个过程):curriculum learning 回到模型的结构中: 1.大结构: (1)图学习层计算邻接矩阵。 (2)输入数据首先通过1*1卷积核到时间卷积,再到图卷积(图卷积实际山接受三个输入:图学习层,上一层时间卷积的输出,以及时间卷积前解一个残差链接快),实际上一组操作包括了一个时间卷积核图卷积。经过n次操作。每次操作都会产生一个输出,把每次操作的输出连接在一起。时间卷积就是在序列维度处理数据,图卷积就是在图维度处理数据。 2.具体组件 (1)图学习层-通过抽样分组方法计算节点间关系,避免内存溢出-并通过一种新的度量方式确定单向距离(单向网络) (2)图卷积层-似乎有点类似gru一样提取上层信息-成为“ 混合跳传播层” (3)时间卷积模块-一维空洞卷积-inception--1*2 ,1*3,1*6,1*7,用这些卷积来覆盖7,12,24,28.60这样的时间周期--用扩张卷积来加大感受野使得可以提取长时间的特征 对比了几个主流结构,都取得了不错的结果。并进行了消融实验验证。消融实验验证:图卷积模块,mix-hop链接,inception,curriculum learning;并单独额外研究了图学习层。
Abstract:
Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate time … >>>
Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate time series forecasting is that its variables depend on one another but, upon looking closely, it is fair to say that existing methods fail to fully exploit latent spatial dependencies between pairs of variables. In recent years, meanwhile, graph neural networks (GNNs) have shown high capability in handling relational dependencies. GNNs require well-defined graph structures for information propagation which means they cannot be applied directly for multivariate time series where the dependencies are not known in advance. In this paper, we propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module, into which external knowledge like variable attributes can be easily integrated. A novel mix-hop propagation layer and a dilated inception layer are further proposed to capture the spatial and temporal dependencies within the time series. The graph learning, graph convolution, and temporal convolution modules are jointly learned in an end-to-end framework. Experimental results show that our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets and achieves on-par performance with other approaches on two traffic datasets which provide extra structural information. <<<
翻译
回到顶部