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

02/04/2018
by   Federico Monti, et al.
0

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.

READ FULL TEXT
research
07/21/2019

Spectral-based Graph Convolutional Network for Directed Graphs

Graph convolutional networks(GCNs) have become the most popular approach...
research
02/27/2018

Metric preserving directed graph symmetrization

This work presents a new method for symmetrization of directed graphs th...
research
05/26/2022

SigMaNet: One Laplacian to Rule Them All

This paper introduces SigMaNet, a generalized Graph Convolutional Networ...
research
04/29/2020

Directed Graph Convolutional Network

Graph Convolutional Networks (GCNs) have been widely used due to their o...
research
02/25/2019

GraphFlow: A New Graph Convolutional Network Based on Parallel Flows

In view of the huge success of convolution neural networks (CNN) for ima...
research
05/27/2019

On Asymptotic Behaviors of Graph CNNs from Dynamical Systems Perspective

Graph Convolutional Neural Networks (graph CNNs) are a promising deep le...
research
10/23/2020

Not Half Bad: Exploring Half-Precision in Graph Convolutional Neural Networks

With the growing significance of graphs as an effective representation o...

Please sign up or login with your details

Forgot password? Click here to reset