Multiple graph kernel learning based on GMDH-type neural network

Lixiang Xu, Lu Bai, Jin Xiao, Qi Liu, Enhong Chen, Xiaofeng Wang, Yuanyan Tang

Abstract: Highlights•We propose a unitized symmetric regularity criterion.•We define a novel structure of initial model of GMDH-NN.•We use graph kernel SVM as base learner and integrate it with GMDH.•We design a special MGKL approach based on the GMDH-NN.•We use several scoring sorting methodologies to evaluate our experiments.