MotifNet: a motif-based Graph Convolutional Network for directed graphs

by   Federico Monti, et al.

Deep learning on graphs and in particular, graph convolutional neural networks, have recently attracted significant attention in the machine learning community. Many of such techniques explore the analogy between the graph Laplacian eigenvectors and the classical Fourier basis, allowing to formulate the convolution as a multiplication in the spectral domain. One of the key drawback of spectral CNNs is their explicit assumption of an undirected graph, leading to a symmetric Laplacian matrix with orthogonal eigendecomposition. In this work we propose MotifNet, a graph CNN capable of dealing with directed graphs by exploiting local graph motifs. We present experimental evidence showing the advantage of our approach on real data.


Spectral-based Graph Convolutional Network for Directed Graphs

Graph convolutional networks(GCNs) have become the most popular approach...

Metric preserving directed graph symmetrization

This work presents a new method for symmetrization of directed graphs th...

SigMaNet: One Laplacian to Rule Them All

This paper introduces SigMaNet, a generalized Graph Convolutional Networ...

Directed Graph Convolutional Network

Graph Convolutional Networks (GCNs) have been widely used due to their o...

GraphFlow: A New Graph Convolutional Network Based on Parallel Flows

In view of the huge success of convolution neural networks (CNN) for ima...

On Asymptotic Behaviors of Graph CNNs from Dynamical Systems Perspective

Graph Convolutional Neural Networks (graph CNNs) are a promising deep le...

Signature-Graph Networks

We propose a novel approach for visual representation learning called Si...