Here, we introduced a computational framework named as ReHoGCNES, aimed at prospective miRNA-disease association prediction (ReHoGCNES-MDA). This method constructs homogenous graph convolutional network with regular graph structure (ReHoGCN) encompassing disease similarity network, miRNA similarity network, and known miRNA-disease association network and then was tested on four experimental tasks. A random edge sampler strategy was utilized to hasten processes and diminish training complexity. Experimental results demonstrate that the proposed ReHoGCNES-MDA method has achieved better results than homogenous graph convolutional network and heterogeneous graph convolutional network with unregular graph structure in all four tasks which implicitly reveals steadily degree distribution of a graph does play an important role in enhancement of model performance.