Inference error versus number of random invalid edges (without valid edges) provided. The proportional error (i.e., inference error) denotes the minimal cross-validation error divided by the minimal least-squares error of the linear regression without any regularization terms and averaged over five random networks. The red, blue and green curves represent 4, 6 and 10 observations, respectively. Providing invalid network edges only has little effect on the errors, especially when many observations are available. The errors become smaller as the number of observations increases, which is consistent with the results in Figure 1.