Graph convolutional networks (GCNs) are powerful tools for graph-structured data. However, they have been recently shown to be vulnerable topological attacks. To enhance adversarial robustness, we go beyond spectral graph theory robust theory. By challenging the classical Laplacian, propose a new convolution operator that is provably in domain and incorporated GCN architecture improve expressiv...

Power shapes relations within social contexts—often with relevant consequences for those lower and higher in power. To inspire novel ideas dialogue on this topic, special issue presents a collection of articles that illustrates important aspects power research have often received little attention to date. Specifically, we present four that, from our perspective, now as well the future can contr...