Caltech scientists have found a fast and efficient way to add up large numbers of Feynman diagrams, the simple drawings ...

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 networks ...

The state of the art in consensus control for multi-agent Euler-Lagrange (EL) systems relies on one or several of the following assumptions: the graph is undirected or directed and strongly connected, ...