Deep graph convolutional network for US birth data harmonization

Lishan Yu, Hamisu M. Salihu, Deepa Dongarwar, Luyao Chen, Xiaoqian Jiang

Abstract: Highlights•An effective way to reduce the manual effort in database harmonization.•An unsupervised deep-learning framework to combine 49-year US natality databases.•A slack margin for the loss function benefits learning the similarities of variables.•A banlist mechanism blocking marginal linkages to increase the efficiency of model.