Graph Classification with 2D Convolutional Neural Networks

ICLR 2018 Antoine Jean-Pierre TixierGiannis NikolentzosPolykarpos MeladianosMichalis 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... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.