A Study on Graph-Structured Recurrent Neural Networks and Sparsification with Application to Epidemic Forecasting

02/13/2019

∙

by   Zhijian Li, et al.

∙

27

∙

share

We study epidemic forecasting on real-world health data by a graph-structured recurrent neural network (GSRNN). We achieve state-of-the-art forecasting accuracy on the benchmark CDC dataset. To improve model efficiency, we sparsify the network weights via transformed-ℓ_1 penalty and maintain prediction accuracy at the same level with 70