Alessio Micheli

TL;DR: The new model allows the extension of the input domain for supervised neural networks to a general class of graphs including both acyclic/cyclic, directed/undirected labeled graphs and can realize adaptive contextual transductions, learning the mapping from graphs for both classification and regression tasks.

TL;DR: It turns out that a deep layering of recurrent models allows an effective diversification of temporal representations in the layers of the hierarchy, by amplifying the effects of the factors influencing the time-scales and the richness of the dynamics, measured as the entropy of recurrent units activations.

TL;DR: By comparing GNNs with structure-agnostic baselines the authors provide convincing evidence that, on some datasets, structural information has not been exploited yet and can contribute to the development of the graph learning field, by providing a much needed grounding for rigorous evaluations of graph classification models.

TL;DR: The paper takes a top-down view of the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing and introduces the basic building blocks that can be combined to design novel and effective neural models for graphs.

TL;DR: This paper addresses a fundamental open issue in deep learning, namely the question of how to establish the number of layers in recurrent architectures in the form of deep echo state networks (DeepESNs), and provides a novel approach to the architectural design of deep Recurrent Neural Networks using signal frequency analysis.