The aim is to combine the merits of flexible manifold embedding and nonlinear graph-based embedding for semi-supervised learning. The proposed linear method will be flexible since it estimates a ...

Abstract: Graph-based semi-supervised learning (GSSL) has long been a research focus. Traditional methods are generally shallow learners, based on the cluster assumption. Recently, graph convolutional ...

We discuss several fascinating concepts and algorithms in graph theory that arose in the design of a nearly-linear time algorithm for solving diagonally-dominant linear systems. We begin by defining a ...

We present graph partition neural networks (GPNN), an extension of graph neural networks (GNNs) able to handle extremely large graphs. GPNNs alternate between locally propagating information between ...

One common graph used for this purpose is a semi-logarithmic plot where ln(k ... fit a straight line through these points with linear regression if possible. Note that data points should be as close ...