Graph Classification with 2D Convolutional Neural Networks

ICLR 2018 Antoine Jean-Pierre Tixier • Giannis Nikolentzos • Polykarpos Meladianos • Michalis Vazirgiannis

Graph learning is currently dominated by graph kernels, which, while powerful, suffer some significant limitations. Convolutional Neural Networks (CNNs) offer a very appealing alternative, but processing graphs with CNNs is not trivial. To address this challenge, many sophisticated extensions of CNNs have recently been introduced.

Full paper

Evaluation


No evaluation results yet. Help compare this paper to other papers by submitting the tasks and evaluation metrics from the paper.