Deep evidential learning in diffusion convolutional recurrent neural network
Document Type
Article
Publication Date
1-1-2023
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
Identifier
85150457257 (Scopus)
Publication Title
Electronic Research Archive
External Full Text Location
https://doi.org/10.3934/era.2023115
e-ISSN
26881594
First Page
2252
Last Page
2264
Issue
4
Volume
31
Grant
2153311
Fund Ref
National Science Foundation
Recommended Citation
Feng, Zhiyuan; Qi, Kai; Shi, Bin; Mei, Hao; Zheng, Qinghua; and Wei, Hua, "Deep evidential learning in diffusion convolutional recurrent neural network" (2023). Faculty Publications. 2099.
https://digitalcommons.njit.edu/fac_pubs/2099