论文标题
基于图的时空流量预测的不确定性间隔
Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction
论文作者
论文摘要
许多流量预测应用程序依赖于不确定性估计而不是平均预测。统计流量预测文献具有一个完整的子字段，专门用于不确定性建模，但是最近的深度学习流量预测模型要么缺乏此功能，要么做出限制其实用性的特定假设。我们提出了一个时空神经网络，我们提出了分位数图波纳特，该网络经过训练，可以估算以前时间段的测量值，以分位数为条件。我们的密度估计方法已通过神经网络完全参数化，并且内部不使用可能性近似。分位数损耗函数是不对称的，因此可以模拟偏斜的密度。这种方法会产生不确定性估计值，而无需在推理过程中进行采样，例如在蒙特卡洛辍学中，这也使我们的方法也有效。
Many traffic prediction applications rely on uncertainty estimates instead of the mean prediction. Statistical traffic prediction literature has a complete subfield devoted to uncertainty modelling, but recent deep learning traffic prediction models either lack this feature or make specific assumptions that restrict its practicality. We propose Quantile Graph Wavenet, a Spatio-Temporal neural network that is trained to estimate a density given the measurements of previous timesteps, conditioned on a quantile. Our method of density estimation is fully parameterised by our neural network and does not use a likelihood approximation internally. The quantile loss function is asymmetric and this makes it possible to model skewed densities. This approach produces uncertainty estimates without the need to sample during inference, such as in Monte Carlo Dropout, which makes our method also efficient.
