张浩彬
(2022-08-09 17:26):
#paper 10.48550/arXiv.2203.03423
Multivariate Time Series Forecasting with Latent Graph Inference 2022的文章。我觉得比较有意思的是，我感觉作者是把简单的东西套在了一个高级的框架里面（这种写作思路值得学习）文章把多变量预测问题分成了两个路线，一个是全局单变量建模（变量共享），一个是直接全局建模全局预测。而作者说他的办法是在第一个方法的基础上进行模块化扩展。具体来说，就是每个单独序列输入编码器生成隐变量。隐变量三会进入一图结构中然后得到隐变量的预测输出。再将输出解码得到最终输出。然后作者说中间的图结构，我们有两种方式，一种是全连接图网络（FC-GNN），一种是二分法图网络（BP-GNN）（我理解是GNN中聚类的一种变体，至于多少类别，则是一个超参数）。这种思路，显然效率会有很大的提升，即使是作者提到的全局GNN，因为只是对隐变量作图，效率也是有提升，更不要说通过抽样构造子图了。所以比起基线模型效率最高，完全可以理解。倒是在准确率的讨论上，实际上作者提出的网络也不全是最优的（两个数据集，一个大部分最优，另一个不是）。虽然做了个简单的消融实验，但是作者也没怎么解释。
总结下来几点：
（1）往上套一个大框架：多变量预测分成两种；embedding变成隐变量；图模型中提供了全连接+二分图的性能-效率权衡()
（2）实验不够，加模拟（这一点还真类似统计中oracle性质的讨论，貌似在深度学习的会议中相对少见）
arXiv,
2022.
DOI: 10.48550/arXiv.2203.03423
Multivariate Time Series Forecasting with Latent Graph Inference
翻译
Abstract:
This paper introduces a new approach for Multivariate Time Series forecasting that jointly infers and leverages relations among time series. Its modularity allows it to be integrated with current univariate methods. Our approach allows to trade-off accuracy and computational efficiency gradually via offering on one extreme inference of a potentially fully-connected graph or on another extreme a bipartite graph. In the potentially fully-connected case we consider all pair-wise interactions among time-series which yields the best forecasting accuracy. Conversely, the bipartite case leverages the dependency structure by inter-communicating the N time series through a small set of K auxiliary nodes that we introduce. This reduces the time and memory complexity w.r.t. previous graph inference methods from O(N^2) to O(NK) with a small trade-off in accuracy. We demonstrate the effectiveness of our model in a variety of datasets where both of its variants perform better or very competitively to previous graph inference methods in terms of forecasting accuracy and time efficiency.
翻译