Despite achieving remarkable performance, deep graph learning models, such as node classification and network embedding, suffer from harassment caused by small adversarial perturbations.

Graph property prediction tasks are important and numerous.

Inthiswork,wedemonstrate that the landscape can be significantly simplified by taking a general approach of mapping a graph to a sequence of tokens and pointers.

Machine learning models based on temporal point processes arethe state ofthe artinawide variety ofapplications involving discrete events incontinuous time.

Inemergent communication studies, one often considers agents who canshare information about a set of objects described by the common features.

Specifically,weshowthatthebound is related to the perturbation/noise level and the recovery of the true support of the leading eigenvector as well. We also investigate the estimator of SGEP via imposing a non-convex regularization. Such estimator can achieve the optimal error rate and can recover the sparsity structure as well.