Algorithm 1 ERGCN

Input: Gene expression matrix $X\in R^{m\times n}$ with m number of samples whose vector length is n, corresponding true labels $Y\in R^m$, number of epochs e, learning rate $\eta$, dropout rate d. Output: Predicted labels Y.  1.Use Equation (1) to calculate the correlation between samples based on gene expression data to get the correlation matrix A (m * m).  2.Given a threshold $\theta$, set the value of the matrix A greater than $\theta$ to 1, and set other values to 0 to obtain the adjacency matrix $\overline{\mathrm{A}}$ (m * m).  3.For i = 1 to epochs do:   H(1) =ReLU( GCN1(X, $\overline{\mathrm{A}}$)   H(p) = H(1) + ReLU(linear(X))   H(2) = GCN2(H(p), $\overline{\mathrm{A}}$)   out = Softmax(H(2))   Calculate the Loss by Equation (4).   Update the weights of ERGCN by gradient descent and back propagation.   end for  4.H(1) =ReLU( GCN1(X, $\overline{\mathrm{A}}$)  5.H(p) = H(1) + ReLU(linear(X))  6.H(2) = GCN2(H(p), $\overline{\mathrm{A}}$)  7.out = Softmax(H(2))  8.Labels = out.max(dim = 1)  9.Return labels