@article{Feng2023, 
author = {Zhiyuan Feng and Kai Qi and Bin Shi and Hao Mei and Qinghua Zheng and Hua Wei},
title = {Deep evidential learning in diffusion convolutional recurrent neural network},
year = {2023},
journal = {Electronic Research Archive},
volume = {31},
number = {4},
pages = {2252-2264},
keywords = {uncertainty quantification, evidential deep learning, graph neural network, spatiotemporal forecasting, regression task},
url = {https://www.sciopen.com/article/10.3934/era.2023115},
doi = {10.3934/era.2023115},
abstract = {Graph neural networks (GNNs) is applied successfully in many graph tasks, but there still exists a limitation that many of GNNs model do not consider uncertainty quantification of its output predictions. For uncertainty quantification, there are mainly two types of methods which are frequentist and Bayesian. But both methods need to sampling to gradually approximate the real distribution, in contrast, evidential deep learning formulates learning as an evidence acquisition process, which could get uncertainty quantification by placing evidential priors over the original Gaussian likelihood function and training the NN to infer the hyperparameters of the evidential distribution without sampling. So evidential deep learning (EDL) has its own advantage in measuring uncertainty. We apply it with diffusion convolutional recurrent neural network (DCRNN), and do the experiment in spatiotemporal forecasting task in a real-world traffic dataset. And we choose mean interval scores (MIS), a good metric for uncertainty quantification. We summarized the advantages of each method.}
}